GSM-Infinite-Leaderboard / data /processed_results.csv
atlas5301
update data
48f162c
dataset,model,length,op,accuracy
symbolic,o1-mini,0,1,0.98
symbolic,o1-mini,0,11,1.0
symbolic,o1-mini,0,21,0.9
symbolic,o1-mini,0,31,0.64
symbolic,o1-mini,0,41,0.54
symbolic,o1-mini,0,51,0.46
symbolic,o1-mini,0,61,0.28
symbolic,o1-mini,0,71,0.24
symbolic,o1-mini,0,81,0.12
symbolic,o1-mini,0,91,0.08
symbolic,o1-mini,0,101,0.06
symbolic,o1-mini,0,111,0.08
symbolic,o1-mini,0,121,0.06
symbolic,o1-mini,0,131,0.02
symbolic,o1-mini,0,141,0.08
symbolic,o1-mini,0,151,0.02
realistic_Medium,mistral-large-2411,0,2,0.9219
realistic_Medium,mistral-large-2411,0,4,0.9844
realistic_Medium,mistral-large-2411,0,6,0.9688
realistic_Medium,mistral-large-2411,0,8,0.9375
realistic_Medium,mistral-large-2411,0,10,0.7422
realistic_Medium,mistral-large-2411,0,12,0.7266
realistic_Medium,mistral-large-2411,0,14,0.7578
realistic_Medium,mistral-large-2411,0,16,0.5703
realistic_Medium,mistral-large-2411,0,18,0.6719
realistic_Medium,mistral-large-2411,0,20,0.5625
realistic_Medium,mistral-large-2411,0,22,0.6172
realistic_Medium,mistral-large-2411,0,24,0.5469
realistic_Medium,mistral-large-2411,0,26,0.5625
realistic_Medium,mistral-large-2411,0,28,0.5312
realistic_Medium,mistral-large-2411,0,30,0.5078
realistic_Medium,mistral-large-2411,0,35,0.346154
realistic_Medium,mistral-large-2411,0,40,0.375
realistic_Medium,mistral-large-2411,0,45,0.298077
realistic_Medium,mistral-large-2411,0,50,0.25
realistic_Medium,mistral-large-2411,0,55,0.0865385
realistic_Medium,mistral-large-2411,0,60,0.125
realistic_Medium,mistral-large-2411,0,65,0.0576923
realistic_Medium,mistral-large-2411,0,70,0.0192308
realistic_Medium,mistral-large-2411,8000,2,0.8438
realistic_Medium,mistral-large-2411,8000,4,0.9141
realistic_Medium,mistral-large-2411,8000,6,0.8672
realistic_Medium,mistral-large-2411,8000,8,0.6641
realistic_Medium,mistral-large-2411,8000,10,0.5625
realistic_Medium,mistral-large-2411,8000,12,0.4453
realistic_Medium,mistral-large-2411,8000,14,0.3984
realistic_Medium,mistral-large-2411,8000,16,0.1719
realistic_Medium,mistral-large-2411,8000,18,0.2891
realistic_Medium,mistral-large-2411,8000,20,0.2656
realistic_Medium,mistral-large-2411,8000,22,0.2266
realistic_Medium,mistral-large-2411,8000,24,0.2578
realistic_Medium,mistral-large-2411,8000,26,0.1875
realistic_Medium,mistral-large-2411,8000,28,0.2188
realistic_Medium,mistral-large-2411,8000,30,0.2677
realistic_Medium,mistral-large-2411,16000,2,0.7188
realistic_Medium,mistral-large-2411,16000,6,0.8125
realistic_Medium,mistral-large-2411,16000,10,0.3906
realistic_Medium,mistral-large-2411,16000,14,0.3047
realistic_Medium,mistral-large-2411,16000,18,0.1953
realistic_Medium,mistral-large-2411,16000,22,0.0703
realistic_Medium,mistral-large-2411,16000,26,0.0938
realistic_Medium,mistral-large-2411,16000,30,0.0394
realistic_Medium,mistral-large-2411,32000,2,0.4882
realistic_Medium,mistral-large-2411,32000,6,0.5938
realistic_Medium,mistral-large-2411,32000,10,0.2422
realistic_Medium,mistral-large-2411,32000,14,0.1406
realistic_Medium,mistral-large-2411,32000,18,0.0783
realistic_Medium,mistral-large-2411,32000,22,0.0583
realistic_Medium,mistral-large-2411,32000,26,0.0078
realistic_Medium,mistral-large-2411,32000,30,0.0078
realistic_Hard,qwen-2.5-72b-instruct,0,2,0.9
realistic_Hard,qwen-2.5-72b-instruct,0,3,0.935
realistic_Hard,qwen-2.5-72b-instruct,0,4,0.91
realistic_Hard,qwen-2.5-72b-instruct,0,5,0.885
realistic_Hard,qwen-2.5-72b-instruct,0,6,0.885
realistic_Hard,qwen-2.5-72b-instruct,0,7,0.795
realistic_Hard,qwen-2.5-72b-instruct,0,8,0.88
realistic_Hard,qwen-2.5-72b-instruct,0,9,0.845
realistic_Hard,qwen-2.5-72b-instruct,0,10,0.805
realistic_Hard,qwen-2.5-72b-instruct,0,11,0.72
realistic_Hard,qwen-2.5-72b-instruct,0,12,0.63
realistic_Hard,qwen-2.5-72b-instruct,0,13,0.695
realistic_Hard,qwen-2.5-72b-instruct,0,14,0.735
realistic_Hard,qwen-2.5-72b-instruct,0,15,0.67
realistic_Hard,qwen-2.5-72b-instruct,0,16,0.71
realistic_Hard,qwen-2.5-72b-instruct,0,17,0.58
realistic_Hard,qwen-2.5-72b-instruct,0,18,0.66
realistic_Hard,qwen-2.5-72b-instruct,0,19,0.54
realistic_Hard,qwen-2.5-72b-instruct,0,20,0.58
realistic_Hard,qwen-2.5-72b-instruct,0,21,0.465
realistic_Hard,qwen-2.5-72b-instruct,0,22,0.415
realistic_Hard,qwen-2.5-72b-instruct,0,23,0.46
realistic_Hard,qwen-2.5-72b-instruct,0,24,0.37
realistic_Hard,qwen-2.5-72b-instruct,0,25,0.395
realistic_Hard,qwen-2.5-72b-instruct,0,26,0.31
realistic_Hard,qwen-2.5-72b-instruct,0,27,0.275
realistic_Hard,qwen-2.5-72b-instruct,0,28,0.315
realistic_Hard,qwen-2.5-72b-instruct,0,29,0.41
realistic_Hard,qwen-2.5-72b-instruct,0,30,0.29
realistic_Hard,qwen-2.5-72b-instruct,0,35,0.16875
realistic_Hard,qwen-2.5-72b-instruct,0,40,0.06875
realistic_Hard,qwen-2.5-72b-instruct,0,45,0.09375
realistic_Hard,qwen-2.5-72b-instruct,0,50,0.05
realistic_Hard,qwen-2.5-72b-instruct,0,55,0.025
realistic_Hard,qwen-2.5-72b-instruct,8000,2,0.765
realistic_Hard,qwen-2.5-72b-instruct,8000,4,0.85
realistic_Hard,qwen-2.5-72b-instruct,8000,6,0.78
realistic_Hard,qwen-2.5-72b-instruct,8000,8,0.665
realistic_Hard,qwen-2.5-72b-instruct,8000,10,0.595
realistic_Hard,qwen-2.5-72b-instruct,8000,12,0.56
realistic_Hard,qwen-2.5-72b-instruct,8000,14,0.44
realistic_Hard,qwen-2.5-72b-instruct,8000,16,0.415
realistic_Hard,qwen-2.5-72b-instruct,8000,18,0.37
realistic_Hard,qwen-2.5-72b-instruct,8000,20,0.35
realistic_Hard,qwen-2.5-72b-instruct,8000,22,0.34
realistic_Hard,qwen-2.5-72b-instruct,8000,24,0.335
realistic_Hard,qwen-2.5-72b-instruct,8000,26,0.31
realistic_Hard,qwen-2.5-72b-instruct,8000,28,0.295
realistic_Hard,qwen-2.5-72b-instruct,8000,30,0.27
realistic_Hard,qwen-2.5-72b-instruct,16000,2,0.7344
realistic_Hard,qwen-2.5-72b-instruct,16000,4,0.7656
realistic_Hard,qwen-2.5-72b-instruct,16000,6,0.7266
realistic_Hard,qwen-2.5-72b-instruct,16000,8,0.625
realistic_Hard,qwen-2.5-72b-instruct,16000,10,0.5391
realistic_Hard,qwen-2.5-72b-instruct,16000,12,0.4141
realistic_Hard,qwen-2.5-72b-instruct,16000,14,0.2812
realistic_Hard,qwen-2.5-72b-instruct,16000,16,0.1719
realistic_Hard,qwen-2.5-72b-instruct,16000,18,0.125
realistic_Hard,qwen-2.5-72b-instruct,16000,20,0.1562
realistic_Hard,qwen-2.5-72b-instruct,16000,22,0.0781
realistic_Hard,qwen-2.5-72b-instruct,16000,24,0.0781
realistic_Hard,qwen-2.5-72b-instruct,16000,26,0.0547
realistic_Hard,qwen-2.5-72b-instruct,16000,28,0.0234
realistic_Hard,qwen-2.5-72b-instruct,16000,30,0.0781
realistic_Hard,qwen-2.5-72b-instruct,32000,2,0.7188
realistic_Hard,qwen-2.5-72b-instruct,32000,4,0.7578
realistic_Hard,qwen-2.5-72b-instruct,32000,6,0.6562
realistic_Hard,qwen-2.5-72b-instruct,32000,8,0.4844
realistic_Hard,qwen-2.5-72b-instruct,32000,10,0.3594
realistic_Hard,qwen-2.5-72b-instruct,32000,12,0.2422
realistic_Hard,qwen-2.5-72b-instruct,32000,14,0.1875
realistic_Hard,qwen-2.5-72b-instruct,32000,16,0.1328
realistic_Hard,qwen-2.5-72b-instruct,32000,18,0.1172
realistic_Hard,qwen-2.5-72b-instruct,32000,20,0.0625
realistic_Hard,qwen-2.5-72b-instruct,32000,22,0.0312
realistic_Hard,qwen-2.5-72b-instruct,32000,24,0.0703
realistic_Hard,qwen-2.5-72b-instruct,32000,26,0.0703
realistic_Hard,qwen-2.5-72b-instruct,32000,28,0.0625
realistic_Hard,qwen-2.5-72b-instruct,32000,30,0.0312
realistic_Hard,deepseek-r1,0,10,0.9453
realistic_Hard,deepseek-r1,0,20,0.9375
realistic_Hard,deepseek-r1,0,30,0.9453
realistic_Hard,deepseek-r1,0,40,0.9231
realistic_Hard,deepseek-r1,0,50,0.8846
realistic_Hard,deepseek-r1,0,60,0.8269
realistic_Hard,deepseek-r1,0,70,0.75
realistic_Hard,deepseek-r1,0,80,0.7404
realistic_Hard,deepseek-r1,0,90,0.6731
realistic_Hard,deepseek-r1,0,100,0.493
realistic_Hard,deepseek-r1,0,110,0.5256
realistic_Hard,deepseek-r1,0,120,0.2658
realistic_Hard,deepseek-r1,0,130,0.2717
symbolic,claude-3.5-sonnet,0,1,0.98
symbolic,claude-3.5-sonnet,0,3,0.99
symbolic,claude-3.5-sonnet,0,5,1.0
symbolic,claude-3.5-sonnet,0,7,0.99
symbolic,claude-3.5-sonnet,0,9,0.98
symbolic,claude-3.5-sonnet,0,11,0.98
symbolic,claude-3.5-sonnet,0,13,0.86
symbolic,claude-3.5-sonnet,0,15,0.77
symbolic,claude-3.5-sonnet,0,17,0.72
symbolic,claude-3.5-sonnet,0,19,0.64
symbolic,claude-3.5-sonnet,0,21,0.44
symbolic,claude-3.5-sonnet,0,23,0.39
symbolic,claude-3.5-sonnet,0,25,0.31
symbolic,claude-3.5-sonnet,0,27,0.27
symbolic,claude-3.5-sonnet,0,29,0.22
symbolic,claude-3.5-sonnet,0,31,0.12
symbolic,claude-3.5-sonnet,0,33,0.17
symbolic,claude-3.5-sonnet,0,35,0.04
symbolic,claude-3.5-sonnet,0,37,0.07
symbolic,claude-3.5-sonnet,0,39,0.08
symbolic,claude-3.5-sonnet,0,41,0.08
symbolic,claude-3.5-sonnet,0,43,0.03
symbolic,claude-3.5-sonnet,0,45,0.04
symbolic,claude-3.5-sonnet,0,47,0.05
symbolic,claude-3.5-sonnet,0,49,0.02
symbolic,claude-3.5-sonnet,0,51,0.02
symbolic,claude-3.5-sonnet,0,53,0.01
symbolic,claude-3.5-sonnet,0,55,0.0
symbolic,claude-3.5-sonnet,0,57,0.02
symbolic,claude-3.5-sonnet,0,59,0.01
symbolic,claude-3.5-sonnet-0620,0,1,1.0
symbolic,claude-3.5-sonnet-0620,0,3,1.0
symbolic,claude-3.5-sonnet-0620,0,5,1.0
symbolic,claude-3.5-sonnet-0620,0,7,1.0
symbolic,claude-3.5-sonnet-0620,0,9,0.97
symbolic,claude-3.5-sonnet-0620,0,11,0.93
symbolic,claude-3.5-sonnet-0620,0,13,0.91
symbolic,claude-3.5-sonnet-0620,0,15,0.88
symbolic,claude-3.5-sonnet-0620,0,17,0.73
symbolic,claude-3.5-sonnet-0620,0,19,0.64
symbolic,claude-3.5-sonnet-0620,0,21,0.57
symbolic,claude-3.5-sonnet-0620,0,23,0.5
symbolic,claude-3.5-sonnet-0620,0,25,0.44
symbolic,claude-3.5-sonnet-0620,0,27,0.4
symbolic,claude-3.5-sonnet-0620,0,29,0.39
symbolic,claude-3.5-sonnet-0620,0,31,0.28
symbolic,claude-3.5-sonnet-0620,0,33,0.3
symbolic,claude-3.5-sonnet-0620,0,35,0.15
symbolic,claude-3.5-sonnet-0620,0,37,0.17
symbolic,claude-3.5-sonnet-0620,0,39,0.11
symbolic,claude-3.5-sonnet-0620,0,41,0.16
symbolic,claude-3.5-sonnet-0620,0,43,0.1
symbolic,claude-3.5-sonnet-0620,0,45,0.07
symbolic,claude-3.5-sonnet-0620,0,47,0.07
symbolic,claude-3.5-sonnet-0620,0,49,0.1
symbolic,claude-3.5-sonnet-0620,0,51,0.03
symbolic,claude-3.5-sonnet-0620,0,53,0.04
symbolic,claude-3.5-sonnet-0620,0,55,0.02
symbolic,claude-3.5-sonnet-0620,0,57,0.04
symbolic,claude-3.5-sonnet-0620,0,59,0.02
realistic_Medium,gpt-4o-mini,0,2,0.762
realistic_Medium,gpt-4o-mini,0,4,0.9194
realistic_Medium,gpt-4o-mini,0,6,0.9113
realistic_Medium,gpt-4o-mini,0,10,0.7863
realistic_Medium,gpt-4o-mini,0,12,0.6008
realistic_Medium,gpt-4o-mini,0,12,0.5444
realistic_Medium,gpt-4o-mini,0,14,0.5444
realistic_Medium,gpt-4o-mini,0,16,0.4234
realistic_Medium,gpt-4o-mini,0,18,0.371
realistic_Medium,gpt-4o-mini,0,20,0.371
realistic_Medium,gpt-4o-mini,0,20,0.3024
realistic_Medium,gpt-4o-mini,0,22,0.1492
realistic_Medium,gpt-4o-mini,0,24,0.1492
realistic_Medium,gpt-4o-mini,0,26,0.1331
realistic_Medium,gpt-4o-mini,0,28,0.0766
realistic_Medium,gpt-4o-mini,0,30,0.0806
realistic_Medium,gpt-4o-mini,0,35,0.0769231
realistic_Medium,gpt-4o-mini,0,40,0.0769231
realistic_Medium,gpt-4o-mini,8000,2,0.4531
realistic_Medium,gpt-4o-mini,8000,4,0.7969
realistic_Medium,gpt-4o-mini,8000,6,0.7266
realistic_Medium,gpt-4o-mini,8000,8,0.4844
realistic_Medium,gpt-4o-mini,8000,10,0.25
realistic_Medium,gpt-4o-mini,8000,12,0.2109
realistic_Medium,gpt-4o-mini,8000,14,0.1094
realistic_Medium,gpt-4o-mini,8000,16,0.0781
realistic_Medium,gpt-4o-mini,8000,18,0.0547
realistic_Medium,gpt-4o-mini,8000,20,0.0156
realistic_Medium,gpt-4o-mini,8000,22,0.0469
realistic_Medium,gpt-4o-mini,8000,24,0.0391
realistic_Medium,gpt-4o-mini,8000,26,0.0938
realistic_Medium,gpt-4o-mini,8000,28,0.0234
realistic_Medium,gpt-4o-mini,8000,30,0.0234
realistic_Medium,gpt-4o-mini,16000,2,0.5078
realistic_Medium,gpt-4o-mini,16000,4,0.7656
realistic_Medium,gpt-4o-mini,16000,6,0.6719
realistic_Medium,gpt-4o-mini,16000,8,0.4141
realistic_Medium,gpt-4o-mini,16000,10,0.1484
realistic_Medium,gpt-4o-mini,16000,12,0.0859
realistic_Medium,gpt-4o-mini,16000,14,0.125
realistic_Medium,gpt-4o-mini,16000,16,0.0391
realistic_Medium,gpt-4o-mini,16000,18,0.0234
realistic_Medium,gpt-4o-mini,16000,20,0.0312
realistic_Medium,gpt-4o-mini,16000,22,0.0391
realistic_Medium,gpt-4o-mini,16000,24,0.0625
realistic_Medium,gpt-4o-mini,16000,26,0.0703
realistic_Medium,gpt-4o-mini,16000,28,0.0469
realistic_Medium,gpt-4o-mini,16000,30,0.0469
realistic_Medium,gpt-4o-mini,32000,2,0.4531
realistic_Medium,gpt-4o-mini,32000,4,0.6719
realistic_Medium,gpt-4o-mini,32000,6,0.5469
realistic_Medium,gpt-4o-mini,32000,8,0.3125
realistic_Medium,gpt-4o-mini,32000,10,0.0703
realistic_Medium,gpt-4o-mini,32000,12,0.1094
realistic_Medium,gpt-4o-mini,32000,14,0.0234
realistic_Medium,gpt-4o-mini,32000,16,0.0234
realistic_Medium,gpt-4o-mini,32000,18,0.0547
realistic_Medium,gpt-4o-mini,32000,20,0.0312
realistic_Medium,gpt-4o-mini,32000,22,0.0469
realistic_Medium,gpt-4o-mini,32000,24,0.0391
realistic_Medium,gpt-4o-mini,32000,26,0.0625
realistic_Medium,gpt-4o-mini,32000,28,0.0391
realistic_Medium,gpt-4o-mini,32000,30,0.0312
realistic_Medium,qwen-2.5-72b-instruct,0,2,0.97
realistic_Medium,qwen-2.5-72b-instruct,0,3,0.88
realistic_Medium,qwen-2.5-72b-instruct,0,4,0.98
realistic_Medium,qwen-2.5-72b-instruct,0,5,0.95
realistic_Medium,qwen-2.5-72b-instruct,0,6,0.97
realistic_Medium,qwen-2.5-72b-instruct,0,7,0.975
realistic_Medium,qwen-2.5-72b-instruct,0,8,0.9
realistic_Medium,qwen-2.5-72b-instruct,0,9,0.975
realistic_Medium,qwen-2.5-72b-instruct,0,10,0.815
realistic_Medium,qwen-2.5-72b-instruct,0,11,0.855
realistic_Medium,qwen-2.5-72b-instruct,0,12,0.705
realistic_Medium,qwen-2.5-72b-instruct,0,13,0.74
realistic_Medium,qwen-2.5-72b-instruct,0,14,0.73
realistic_Medium,qwen-2.5-72b-instruct,0,15,0.755
realistic_Medium,qwen-2.5-72b-instruct,0,16,0.61
realistic_Medium,qwen-2.5-72b-instruct,0,17,0.67
realistic_Medium,qwen-2.5-72b-instruct,0,18,0.66
realistic_Medium,qwen-2.5-72b-instruct,0,19,0.615
realistic_Medium,qwen-2.5-72b-instruct,0,20,0.64
realistic_Medium,qwen-2.5-72b-instruct,0,21,0.595
realistic_Medium,qwen-2.5-72b-instruct,0,22,0.61
realistic_Medium,qwen-2.5-72b-instruct,0,23,0.515
realistic_Medium,qwen-2.5-72b-instruct,0,24,0.595
realistic_Medium,qwen-2.5-72b-instruct,0,25,0.485
realistic_Medium,qwen-2.5-72b-instruct,0,26,0.45
realistic_Medium,qwen-2.5-72b-instruct,0,27,0.435
realistic_Medium,qwen-2.5-72b-instruct,0,28,0.44
realistic_Medium,qwen-2.5-72b-instruct,0,29,0.385
realistic_Medium,qwen-2.5-72b-instruct,0,30,0.365
realistic_Medium,qwen-2.5-72b-instruct,0,35,0.30625
realistic_Medium,qwen-2.5-72b-instruct,0,40,0.19375
realistic_Medium,qwen-2.5-72b-instruct,0,45,0.18125
realistic_Medium,qwen-2.5-72b-instruct,0,50,0.125
realistic_Medium,qwen-2.5-72b-instruct,0,55,0.06875
realistic_Medium,qwen-2.5-72b-instruct,0,60,0.03125
realistic_Medium,qwen-2.5-72b-instruct,8000,2,0.825
realistic_Medium,qwen-2.5-72b-instruct,8000,4,0.91
realistic_Medium,qwen-2.5-72b-instruct,8000,6,0.835
realistic_Medium,qwen-2.5-72b-instruct,8000,8,0.745
realistic_Medium,qwen-2.5-72b-instruct,8000,10,0.6
realistic_Medium,qwen-2.5-72b-instruct,8000,12,0.555
realistic_Medium,qwen-2.5-72b-instruct,8000,14,0.48
realistic_Medium,qwen-2.5-72b-instruct,8000,16,0.46
realistic_Medium,qwen-2.5-72b-instruct,8000,18,0.34
realistic_Medium,qwen-2.5-72b-instruct,8000,20,0.325
realistic_Medium,qwen-2.5-72b-instruct,8000,22,0.23
realistic_Medium,qwen-2.5-72b-instruct,8000,24,0.2
realistic_Medium,qwen-2.5-72b-instruct,8000,26,0.155
realistic_Medium,qwen-2.5-72b-instruct,8000,28,0.185
realistic_Medium,qwen-2.5-72b-instruct,8000,30,0.115
realistic_Medium,qwen-2.5-72b-instruct,16000,2,0.7188
realistic_Medium,qwen-2.5-72b-instruct,16000,4,0.8828
realistic_Medium,qwen-2.5-72b-instruct,16000,6,0.8359
realistic_Medium,qwen-2.5-72b-instruct,16000,8,0.625
realistic_Medium,qwen-2.5-72b-instruct,16000,10,0.5781
realistic_Medium,qwen-2.5-72b-instruct,16000,12,0.4375
realistic_Medium,qwen-2.5-72b-instruct,16000,14,0.4062
realistic_Medium,qwen-2.5-72b-instruct,16000,16,0.3984
realistic_Medium,qwen-2.5-72b-instruct,16000,18,0.2344
realistic_Medium,qwen-2.5-72b-instruct,16000,20,0.1719
realistic_Medium,qwen-2.5-72b-instruct,16000,22,0.1562
realistic_Medium,qwen-2.5-72b-instruct,16000,24,0.0625
realistic_Medium,qwen-2.5-72b-instruct,16000,26,0.0625
realistic_Medium,qwen-2.5-72b-instruct,16000,28,0.0859
realistic_Medium,qwen-2.5-72b-instruct,16000,30,0.0469
realistic_Medium,qwen-2.5-72b-instruct,32000,2,0.7344
realistic_Medium,qwen-2.5-72b-instruct,32000,4,0.8047
realistic_Medium,qwen-2.5-72b-instruct,32000,6,0.6875
realistic_Medium,qwen-2.5-72b-instruct,32000,8,0.5547
realistic_Medium,qwen-2.5-72b-instruct,32000,10,0.5625
realistic_Medium,qwen-2.5-72b-instruct,32000,12,0.4219
realistic_Medium,qwen-2.5-72b-instruct,32000,14,0.3203
realistic_Medium,qwen-2.5-72b-instruct,32000,16,0.2422
realistic_Medium,qwen-2.5-72b-instruct,32000,18,0.1719
realistic_Medium,qwen-2.5-72b-instruct,32000,20,0.1562
realistic_Medium,qwen-2.5-72b-instruct,32000,22,0.0781
realistic_Medium,qwen-2.5-72b-instruct,32000,24,0.0703
realistic_Medium,qwen-2.5-72b-instruct,32000,26,0.0469
realistic_Medium,qwen-2.5-72b-instruct,32000,28,0.0469
realistic_Medium,qwen-2.5-72b-instruct,32000,30,0.0625
symbolic,deepseek-v3,0,1,1.0
symbolic,deepseek-v3,0,6,0.97
symbolic,deepseek-v3,0,11,0.97
symbolic,deepseek-v3,0,16,0.88
symbolic,deepseek-v3,0,21,0.82
symbolic,deepseek-v3,0,26,0.7
symbolic,deepseek-v3,0,31,0.62
symbolic,deepseek-v3,0,36,0.5
symbolic,deepseek-v3,0,41,0.46
symbolic,deepseek-v3,0,46,0.44
symbolic,deepseek-v3,0,51,0.23
symbolic,deepseek-v3,0,56,0.25
symbolic,deepseek-v3,0,61,0.23
symbolic,deepseek-v3,0,66,0.13
symbolic,deepseek-v3,0,71,0.23
symbolic,deepseek-v3,0,76,0.13
symbolic,deepseek-v3,0,81,0.17
symbolic,deepseek-v3,0,86,0.11
symbolic,deepseek-v3,0,91,0.06
symbolic,deepseek-v3,0,96,0.11
symbolic,deepseek-v3,0,101,0.03
symbolic,deepseek-v3,0,106,0.05
symbolic,deepseek-v3,0,111,0.02
symbolic,deepseek-v3,0,116,0.04
symbolic,deepseek-v3,8000,1,0.98
symbolic,deepseek-v3,8000,2,0.83
symbolic,deepseek-v3,8000,3,0.66
symbolic,deepseek-v3,8000,4,0.59
symbolic,deepseek-v3,8000,5,0.43
symbolic,deepseek-v3,8000,6,0.34
symbolic,deepseek-v3,8000,7,0.35
symbolic,deepseek-v3,8000,8,0.28
symbolic,deepseek-v3,8000,9,0.15
symbolic,deepseek-v3,8000,10,0.17
symbolic,deepseek-v3,8000,11,0.11
symbolic,deepseek-v3,8000,12,0.04
symbolic,deepseek-v3,8000,13,0.18
symbolic,deepseek-v3,8000,14,0.09
symbolic,deepseek-v3,8000,15,0.05
symbolic,deepseek-v3,8000,16,0.03
symbolic,deepseek-v3,8000,17,0.08
symbolic,deepseek-v3,8000,18,0.03
symbolic,deepseek-v3,8000,19,0.02
symbolic,deepseek-v3,16000,1,0.98
symbolic,deepseek-v3,16000,2,0.42
symbolic,deepseek-v3,16000,3,0.4
symbolic,deepseek-v3,16000,4,0.22
symbolic,deepseek-v3,16000,5,0.16
symbolic,deepseek-v3,16000,6,0.06
symbolic,deepseek-v3,16000,7,0.06
symbolic,deepseek-v3,16000,8,0.0
symbolic,deepseek-v3,16000,9,0.1
symbolic,deepseek-v3,16000,10,0.06
symbolic,deepseek-v3,16000,11,0.02
symbolic,deepseek-v3,16000,12,0.0
symbolic,deepseek-v3,16000,13,0.0
symbolic,deepseek-v3,16000,14,0.02
symbolic,deepseek-v3,32000,1,0.8
symbolic,deepseek-v3,32000,2,0.2
symbolic,deepseek-v3,32000,3,0.24
symbolic,deepseek-v3,32000,4,0.2
realistic_Hard,llama-3.1-8b-instruct,0,2,0.53
realistic_Hard,llama-3.1-8b-instruct,0,3,0.6
realistic_Hard,llama-3.1-8b-instruct,0,4,0.57
realistic_Hard,llama-3.1-8b-instruct,0,5,0.52
realistic_Hard,llama-3.1-8b-instruct,0,6,0.485
realistic_Hard,llama-3.1-8b-instruct,0,7,0.415
realistic_Hard,llama-3.1-8b-instruct,0,8,0.38
realistic_Hard,llama-3.1-8b-instruct,0,9,0.325
realistic_Hard,llama-3.1-8b-instruct,0,10,0.395
realistic_Hard,llama-3.1-8b-instruct,0,11,0.25
realistic_Hard,llama-3.1-8b-instruct,0,12,0.28
realistic_Hard,llama-3.1-8b-instruct,0,13,0.24
realistic_Hard,llama-3.1-8b-instruct,0,14,0.21
realistic_Hard,llama-3.1-8b-instruct,0,15,0.19
realistic_Hard,llama-3.1-8b-instruct,0,16,0.165
realistic_Hard,llama-3.1-8b-instruct,0,17,0.095
realistic_Hard,llama-3.1-8b-instruct,0,18,0.1
realistic_Hard,llama-3.1-8b-instruct,0,19,0.085
realistic_Hard,llama-3.1-8b-instruct,0,20,0.07
realistic_Hard,llama-3.1-8b-instruct,0,21,0.055
realistic_Hard,llama-3.1-8b-instruct,0,22,0.06
realistic_Hard,llama-3.1-8b-instruct,0,23,0.06
realistic_Hard,llama-3.1-8b-instruct,0,24,0.065
realistic_Hard,llama-3.1-8b-instruct,0,25,0.06
realistic_Hard,llama-3.1-8b-instruct,0,26,0.015
realistic_Hard,llama-3.1-8b-instruct,0,27,0.025
realistic_Hard,llama-3.1-8b-instruct,0,28,0.045
realistic_Hard,llama-3.1-8b-instruct,0,29,0.03
realistic_Hard,llama-3.1-8b-instruct,0,30,0.02
realistic_Hard,llama-3.1-8b-instruct,8000,2,0.465
realistic_Hard,llama-3.1-8b-instruct,8000,4,0.285
realistic_Hard,llama-3.1-8b-instruct,8000,6,0.265
realistic_Hard,llama-3.1-8b-instruct,8000,8,0.165
realistic_Hard,llama-3.1-8b-instruct,8000,10,0.155
realistic_Hard,llama-3.1-8b-instruct,8000,12,0.105
realistic_Hard,llama-3.1-8b-instruct,8000,14,0.08
realistic_Hard,llama-3.1-8b-instruct,8000,16,0.06
realistic_Hard,llama-3.1-8b-instruct,8000,18,0.03
realistic_Hard,llama-3.1-8b-instruct,8000,20,0.055
realistic_Hard,llama-3.1-8b-instruct,8000,22,0.04
realistic_Hard,llama-3.1-8b-instruct,8000,24,0.025
realistic_Hard,llama-3.1-8b-instruct,8000,26,0.015
realistic_Hard,llama-3.1-8b-instruct,8000,28,0.025
realistic_Hard,llama-3.1-8b-instruct,8000,30,0.01
realistic_Hard,llama-3.1-8b-instruct,16000,2,0.38
realistic_Hard,llama-3.1-8b-instruct,16000,4,0.135
realistic_Hard,llama-3.1-8b-instruct,16000,6,0.135
realistic_Hard,llama-3.1-8b-instruct,16000,8,0.145
realistic_Hard,llama-3.1-8b-instruct,16000,10,0.095
realistic_Hard,llama-3.1-8b-instruct,16000,12,0.06
realistic_Hard,llama-3.1-8b-instruct,16000,14,0.05
realistic_Hard,llama-3.1-8b-instruct,16000,16,0.045
realistic_Hard,llama-3.1-8b-instruct,16000,18,0.045
realistic_Hard,llama-3.1-8b-instruct,16000,20,0.035
realistic_Hard,llama-3.1-8b-instruct,16000,22,0.015
realistic_Hard,llama-3.1-8b-instruct,16000,24,0.015
realistic_Hard,llama-3.1-8b-instruct,16000,26,0.035
realistic_Hard,llama-3.1-8b-instruct,16000,28,0.03
realistic_Hard,llama-3.1-8b-instruct,16000,30,0.01
realistic_Hard,llama-3.1-8b-instruct,32000,2,0.31
realistic_Hard,llama-3.1-8b-instruct,32000,4,0.17
realistic_Hard,llama-3.1-8b-instruct,32000,6,0.11
realistic_Hard,llama-3.1-8b-instruct,32000,8,0.05
realistic_Hard,llama-3.1-8b-instruct,32000,10,0.055
realistic_Hard,llama-3.1-8b-instruct,32000,12,0.035
realistic_Hard,llama-3.1-8b-instruct,32000,14,0.045
realistic_Hard,llama-3.1-8b-instruct,32000,16,0.025
realistic_Hard,llama-3.1-8b-instruct,32000,18,0.02
realistic_Hard,llama-3.1-8b-instruct,32000,20,0.035
realistic_Hard,llama-3.1-8b-instruct,32000,22,0.015
realistic_Hard,llama-3.1-8b-instruct,32000,24,0.02
realistic_Hard,llama-3.1-8b-instruct,32000,26,0.0242
realistic_Hard,llama-3.1-8b-instruct,32000,28,0.025
realistic_Hard,llama-3.1-8b-instruct,32000,30,0.01
realistic_Hard,llama-3.1-405b-instruct,0,2,0.765
realistic_Hard,llama-3.1-405b-instruct,0,3,0.805
realistic_Hard,llama-3.1-405b-instruct,0,4,0.755
realistic_Hard,llama-3.1-405b-instruct,0,5,0.79
realistic_Hard,llama-3.1-405b-instruct,0,6,0.85
realistic_Hard,llama-3.1-405b-instruct,0,7,0.655
realistic_Hard,llama-3.1-405b-instruct,0,8,0.74
realistic_Hard,llama-3.1-405b-instruct,0,9,0.71
realistic_Hard,llama-3.1-405b-instruct,0,10,0.585
realistic_Hard,llama-3.1-405b-instruct,0,11,0.475
realistic_Hard,llama-3.1-405b-instruct,0,12,0.455
realistic_Hard,llama-3.1-405b-instruct,0,13,0.445
realistic_Hard,llama-3.1-405b-instruct,0,14,0.405
realistic_Hard,llama-3.1-405b-instruct,0,15,0.395
realistic_Hard,llama-3.1-405b-instruct,0,16,0.32
realistic_Hard,llama-3.1-405b-instruct,0,17,0.22
realistic_Hard,llama-3.1-405b-instruct,0,18,0.195
realistic_Hard,llama-3.1-405b-instruct,0,19,0.125
realistic_Hard,llama-3.1-405b-instruct,0,20,0.04
realistic_Hard,llama-3.1-405b-instruct,0,21,0.075
realistic_Hard,llama-3.1-405b-instruct,0,22,0.03
realistic_Hard,llama-3.1-405b-instruct,0,23,0.005
realistic_Hard,llama-3.1-405b-instruct,0,24,0.01
realistic_Hard,llama-3.1-405b-instruct,0,25,0.005
realistic_Hard,llama-3.1-405b-instruct,0,26,0.01
realistic_Hard,llama-3.1-405b-instruct,0,27,0.01
realistic_Hard,llama-3.1-405b-instruct,0,28,0.0
realistic_Hard,llama-3.1-405b-instruct,0,29,0.005
realistic_Hard,llama-3.1-405b-instruct,0,30,0.005
realistic_Hard,qwen-2.5-7b-instruct,0,2,0.655
realistic_Hard,qwen-2.5-7b-instruct,0,3,0.7
realistic_Hard,qwen-2.5-7b-instruct,0,4,0.65
realistic_Hard,qwen-2.5-7b-instruct,0,5,0.585
realistic_Hard,qwen-2.5-7b-instruct,0,6,0.585
realistic_Hard,qwen-2.5-7b-instruct,0,7,0.465
realistic_Hard,qwen-2.5-7b-instruct,0,8,0.39
realistic_Hard,qwen-2.5-7b-instruct,0,9,0.35
realistic_Hard,qwen-2.5-7b-instruct,0,10,0.285
realistic_Hard,qwen-2.5-7b-instruct,0,11,0.195
realistic_Hard,qwen-2.5-7b-instruct,0,12,0.255
realistic_Hard,qwen-2.5-7b-instruct,0,13,0.21
realistic_Hard,qwen-2.5-7b-instruct,0,14,0.21
realistic_Hard,qwen-2.5-7b-instruct,0,15,0.18
realistic_Hard,qwen-2.5-7b-instruct,0,16,0.11
realistic_Hard,qwen-2.5-7b-instruct,0,17,0.1
realistic_Hard,qwen-2.5-7b-instruct,0,18,0.115
realistic_Hard,qwen-2.5-7b-instruct,0,19,0.03
realistic_Hard,qwen-2.5-7b-instruct,0,20,0.05
realistic_Hard,qwen-2.5-7b-instruct,0,21,0.02
realistic_Hard,qwen-2.5-7b-instruct,0,22,0.055
realistic_Hard,qwen-2.5-7b-instruct,0,23,0.045
realistic_Hard,qwen-2.5-7b-instruct,0,24,0.045
realistic_Hard,qwen-2.5-7b-instruct,0,25,0.025
realistic_Hard,qwen-2.5-7b-instruct,0,26,0.045
realistic_Hard,qwen-2.5-7b-instruct,0,27,0.04
realistic_Hard,qwen-2.5-7b-instruct,0,28,0.035
realistic_Hard,qwen-2.5-7b-instruct,0,29,0.05
realistic_Hard,qwen-2.5-7b-instruct,0,30,0.065
realistic_Hard,qwen-2.5-7b-instruct,8000,2,0.495
realistic_Hard,qwen-2.5-7b-instruct,8000,4,0.365
realistic_Hard,qwen-2.5-7b-instruct,8000,6,0.315
realistic_Hard,qwen-2.5-7b-instruct,8000,8,0.2
realistic_Hard,qwen-2.5-7b-instruct,8000,10,0.17
realistic_Hard,qwen-2.5-7b-instruct,8000,12,0.135
realistic_Hard,qwen-2.5-7b-instruct,8000,14,0.08
realistic_Hard,qwen-2.5-7b-instruct,8000,16,0.07
realistic_Hard,qwen-2.5-7b-instruct,8000,18,0.03
realistic_Hard,qwen-2.5-7b-instruct,8000,20,0.03
realistic_Hard,qwen-2.5-7b-instruct,8000,22,0.025
realistic_Hard,qwen-2.5-7b-instruct,8000,24,0.015
realistic_Hard,qwen-2.5-7b-instruct,8000,26,0.035
realistic_Hard,qwen-2.5-7b-instruct,8000,28,0.03
realistic_Hard,qwen-2.5-7b-instruct,8000,30,0.02
realistic_Hard,qwen-2.5-7b-instruct,16000,2,0.535
realistic_Hard,qwen-2.5-7b-instruct,16000,4,0.26
realistic_Hard,qwen-2.5-7b-instruct,16000,6,0.225
realistic_Hard,qwen-2.5-7b-instruct,16000,8,0.155
realistic_Hard,qwen-2.5-7b-instruct,16000,10,0.1
realistic_Hard,qwen-2.5-7b-instruct,16000,12,0.12
realistic_Hard,qwen-2.5-7b-instruct,16000,14,0.075
realistic_Hard,qwen-2.5-7b-instruct,16000,16,0.05
realistic_Hard,qwen-2.5-7b-instruct,16000,18,0.04
realistic_Hard,qwen-2.5-7b-instruct,16000,20,0.035
realistic_Hard,qwen-2.5-7b-instruct,16000,22,0.06
realistic_Hard,qwen-2.5-7b-instruct,16000,24,0.06
realistic_Hard,qwen-2.5-7b-instruct,16000,26,0.05
realistic_Hard,qwen-2.5-7b-instruct,16000,28,0.035
realistic_Hard,qwen-2.5-7b-instruct,16000,30,0.06
realistic_Hard,qwen-2.5-7b-instruct,32000,2,0.39
realistic_Hard,qwen-2.5-7b-instruct,32000,4,0.245
realistic_Hard,qwen-2.5-7b-instruct,32000,6,0.165
realistic_Hard,qwen-2.5-7b-instruct,32000,8,0.16
realistic_Hard,qwen-2.5-7b-instruct,32000,10,0.11
realistic_Hard,qwen-2.5-7b-instruct,32000,12,0.055
realistic_Hard,qwen-2.5-7b-instruct,32000,14,0.065
realistic_Hard,qwen-2.5-7b-instruct,32000,16,0.045
realistic_Hard,qwen-2.5-7b-instruct,32000,18,0.055
realistic_Hard,qwen-2.5-7b-instruct,32000,20,0.06
realistic_Hard,qwen-2.5-7b-instruct,32000,22,0.085
realistic_Hard,qwen-2.5-7b-instruct,32000,24,0.065
realistic_Hard,qwen-2.5-7b-instruct,32000,26,0.055
realistic_Hard,qwen-2.5-7b-instruct,32000,28,0.045
realistic_Hard,qwen-2.5-7b-instruct,32000,30,0.055
realistic_Medium,gpt-4o-2024-11-20,0,2,0.9375
realistic_Medium,gpt-4o-2024-11-20,0,6,0.9844
realistic_Medium,gpt-4o-2024-11-20,0,10,0.7266
realistic_Medium,gpt-4o-2024-11-20,0,14,0.7188
realistic_Medium,gpt-4o-2024-11-20,0,18,0.6719
realistic_Medium,gpt-4o-2024-11-20,0,22,0.5547
realistic_Medium,gpt-4o-2024-11-20,0,26,0.4375
realistic_Medium,gpt-4o-2024-11-20,0,30,0.3047
realistic_Medium,gpt-4o-2024-11-20,0,35,0.326923
realistic_Medium,gpt-4o-2024-11-20,0,40,0.25
realistic_Medium,gpt-4o-2024-11-20,0,45,0.163462
realistic_Medium,gpt-4o-2024-11-20,0,50,0.0961538
realistic_Medium,gpt-4o-2024-11-20,0,55,0.125
realistic_Medium,gpt-4o-2024-11-20,0,60,0.0576923
symbolic,gemini-1.5-pro-002,0,1,0.99
symbolic,gemini-1.5-pro-002,0,4,0.97
symbolic,gemini-1.5-pro-002,0,7,0.97
symbolic,gemini-1.5-pro-002,0,10,0.93
symbolic,gemini-1.5-pro-002,0,13,0.82
symbolic,gemini-1.5-pro-002,0,16,0.78
symbolic,gemini-1.5-pro-002,0,19,0.72
symbolic,gemini-1.5-pro-002,0,22,0.65
symbolic,gemini-1.5-pro-002,0,25,0.48
symbolic,gemini-1.5-pro-002,0,28,0.28
symbolic,gemini-1.5-pro-002,0,31,0.33
symbolic,gemini-1.5-pro-002,0,34,0.24
symbolic,gemini-1.5-pro-002,0,37,0.18
symbolic,gemini-1.5-pro-002,0,40,0.13
symbolic,gemini-1.5-pro-002,0,43,0.13
symbolic,gemini-1.5-pro-002,0,46,0.11
symbolic,gemini-1.5-pro-002,0,49,0.04
symbolic,gemini-1.5-pro-002,0,52,0.03
symbolic,gemini-1.5-pro-002,0,55,0.04
symbolic,gemini-1.5-pro-002,0,58,0.01
symbolic,gemini-1.5-pro-002,0,61,0.02
symbolic,gemini-1.5-pro-002,0,64,0.02
symbolic,gemini-1.5-pro-002,0,67,0.04
symbolic,gemini-1.5-pro-002,0,70,0.04
symbolic,gemini-1.5-pro-002,0,73,0.01
symbolic,gemini-1.5-pro-002,0,76,0.0
symbolic,gemini-1.5-pro-002,0,79,0.0
symbolic,gemini-1.5-pro-002,0,82,0.02
symbolic,gemini-1.5-pro-002,0,85,0.0
symbolic,gemini-1.5-pro-002,0,88,0.01
symbolic,gemini-1.5-pro-002,8000,1,0.99
symbolic,gemini-1.5-pro-002,8000,2,0.69
symbolic,gemini-1.5-pro-002,8000,3,0.54
symbolic,gemini-1.5-pro-002,8000,4,0.45
symbolic,gemini-1.5-pro-002,8000,5,0.26
symbolic,gemini-1.5-pro-002,8000,6,0.35
symbolic,gemini-1.5-pro-002,8000,7,0.25
symbolic,gemini-1.5-pro-002,8000,8,0.19
symbolic,gemini-1.5-pro-002,8000,9,0.21
symbolic,gemini-1.5-pro-002,8000,10,0.09
symbolic,gemini-1.5-pro-002,8000,11,0.17
symbolic,gemini-1.5-pro-002,8000,12,0.14
symbolic,gemini-1.5-pro-002,8000,13,0.05
symbolic,gemini-1.5-pro-002,8000,14,0.07
symbolic,gemini-1.5-pro-002,8000,16,0.04
symbolic,gemini-1.5-pro-002,8000,17,0.03
symbolic,gemini-1.5-pro-002,8000,18,0.05
symbolic,gemini-1.5-pro-002,8000,19,0.03
symbolic,gemini-1.5-pro-002,16000,1,1.0
symbolic,gemini-1.5-pro-002,16000,2,0.64
symbolic,gemini-1.5-pro-002,16000,3,0.42
symbolic,gemini-1.5-pro-002,16000,4,0.38
symbolic,gemini-1.5-pro-002,16000,5,0.3
symbolic,gemini-1.5-pro-002,16000,6,0.34
symbolic,gemini-1.5-pro-002,16000,7,0.1
symbolic,gemini-1.5-pro-002,16000,8,0.1
symbolic,gemini-1.5-pro-002,16000,9,0.18
symbolic,gemini-1.5-pro-002,16000,10,0.14
symbolic,gemini-1.5-pro-002,16000,11,0.14
symbolic,gemini-1.5-pro-002,16000,12,0.06
symbolic,gemini-1.5-pro-002,16000,13,0.1
symbolic,gemini-1.5-pro-002,16000,14,0.06
symbolic,gemini-1.5-pro-002,32000,1,0.98
symbolic,gemini-1.5-pro-002,32000,2,0.68
symbolic,gemini-1.5-pro-002,32000,3,0.44
symbolic,gemini-1.5-pro-002,32000,4,0.46
symbolic,gemini-1.5-pro-002,32000,5,0.26
symbolic,gemini-1.5-pro-002,32000,6,0.3
symbolic,gemini-1.5-pro-002,32000,7,0.1
symbolic,gemini-1.5-pro-002,32000,8,0.06
symbolic,gemini-1.5-pro-002,32000,9,0.1
symbolic,gemini-1.5-pro-002,32000,10,0.02
symbolic,gemini-1.5-pro-002,32000,11,0.06
symbolic,gemini-1.5-pro-002,32000,12,0.02
symbolic,gemini-1.5-pro-002,32000,13,0.06
symbolic,gemini-1.5-pro-002,32000,14,0.12
realistic_Hard,gemini-1.5-pro-002,0,2,0.9531
realistic_Hard,gemini-1.5-pro-002,0,6,0.9844
realistic_Hard,gemini-1.5-pro-002,0,10,0.8828
realistic_Hard,gemini-1.5-pro-002,0,14,0.7734
realistic_Hard,gemini-1.5-pro-002,0,18,0.7734
realistic_Hard,gemini-1.5-pro-002,0,22,0.5156
realistic_Hard,gemini-1.5-pro-002,0,26,0.3672
realistic_Hard,gemini-1.5-pro-002,0,30,0.2891
realistic_Hard,gemini-1.5-pro-002,0,35,0.25
realistic_Hard,gemini-1.5-pro-002,0,40,0.201923
realistic_Hard,gemini-1.5-pro-002,0,45,0.0865385
realistic_Hard,gemini-1.5-pro-002,0,50,0.0384615
realistic_Hard,gemini-1.5-pro-002,8000,2,0.875
realistic_Hard,gemini-1.5-pro-002,8000,6,0.8203
realistic_Hard,gemini-1.5-pro-002,8000,10,0.6641
realistic_Hard,gemini-1.5-pro-002,8000,14,0.6719
realistic_Hard,gemini-1.5-pro-002,8000,18,0.5312
realistic_Hard,gemini-1.5-pro-002,8000,22,0.5312
realistic_Hard,gemini-1.5-pro-002,8000,26,0.5
realistic_Hard,gemini-1.5-pro-002,8000,30,0.4688
realistic_Hard,gemini-1.5-pro-002,16000,2,0.9219
realistic_Hard,gemini-1.5-pro-002,16000,6,0.7891
realistic_Hard,gemini-1.5-pro-002,16000,10,0.5703
realistic_Hard,gemini-1.5-pro-002,16000,14,0.3438
realistic_Hard,gemini-1.5-pro-002,16000,18,0.3281
realistic_Hard,gemini-1.5-pro-002,16000,22,0.2266
realistic_Hard,gemini-1.5-pro-002,16000,26,0.1719
realistic_Hard,gemini-1.5-pro-002,16000,30,0.125
realistic_Hard,gemini-1.5-pro-002,32000,2,0.8504
realistic_Hard,gemini-1.5-pro-002,32000,6,0.7188
realistic_Hard,gemini-1.5-pro-002,32000,10,0.5197
realistic_Hard,gemini-1.5-pro-002,32000,14,0.4375
realistic_Hard,gemini-1.5-pro-002,32000,18,0.315
realistic_Hard,gemini-1.5-pro-002,32000,22,0.1575
realistic_Hard,gemini-1.5-pro-002,32000,26,0.0391
realistic_Hard,gemini-1.5-pro-002,32000,30,0.0859
realistic_Medium,jamba-1.5-large,0,2,0.6716
realistic_Medium,jamba-1.5-large,0,2,0.7422
realistic_Medium,jamba-1.5-large,0,4,0.6406
realistic_Medium,jamba-1.5-large,0,6,0.3516
realistic_Medium,jamba-1.5-large,0,8,0.1484
realistic_Medium,jamba-1.5-large,0,10,0.1562
realistic_Medium,jamba-1.5-large,0,12,0.1406
realistic_Medium,jamba-1.5-large,0,14,0.0703
realistic_Medium,jamba-1.5-large,0,16,0.0938
realistic_Medium,jamba-1.5-large,0,18,0.0781
realistic_Medium,jamba-1.5-large,0,20,0.0625
realistic_Medium,jamba-1.5-large,0,22,0.0469
realistic_Medium,jamba-1.5-large,0,24,0.0859
realistic_Medium,jamba-1.5-large,0,26,0.0703
realistic_Medium,jamba-1.5-large,0,28,0.0781
realistic_Medium,jamba-1.5-large,0,30,0.0625
symbolic,claude-3.5-haiku,0,1,0.96
symbolic,claude-3.5-haiku,0,3,1.0
symbolic,claude-3.5-haiku,0,5,0.91
symbolic,claude-3.5-haiku,0,7,0.73
symbolic,claude-3.5-haiku,0,9,0.53
symbolic,claude-3.5-haiku,0,11,0.28
symbolic,claude-3.5-haiku,0,13,0.2
symbolic,claude-3.5-haiku,0,15,0.07
symbolic,claude-3.5-haiku,0,17,0.1
symbolic,claude-3.5-haiku,0,19,0.05
symbolic,claude-3.5-haiku,0,21,0.01
symbolic,claude-3.5-haiku,0,23,0.01
symbolic,claude-3.5-haiku,0,25,0.02
symbolic,claude-3.5-haiku,0,27,0.01
symbolic,claude-3.5-haiku,0,29,0.02
symbolic,claude-3.5-haiku,0,31,0.01
symbolic,claude-3.5-haiku,0,33,0.0
symbolic,claude-3.5-haiku,0,35,0.0
symbolic,claude-3.5-haiku,0,37,0.01
symbolic,claude-3.5-haiku,0,39,0.01
symbolic,claude-3.5-haiku,0,41,0.01
symbolic,claude-3.5-haiku,0,43,0.0
symbolic,claude-3.5-haiku,0,45,0.02
symbolic,claude-3.5-haiku,0,47,0.0
symbolic,claude-3.5-haiku,0,49,0.0
symbolic,claude-3.5-haiku,0,51,0.0
symbolic,claude-3.5-haiku,0,53,0.0
symbolic,claude-3.5-haiku,0,55,0.0
symbolic,claude-3.5-haiku,0,57,0.0
symbolic,claude-3.5-haiku,0,59,0.01
symbolic,o3-mini,0,1,1.0
symbolic,o3-mini,0,16,0.96
symbolic,o3-mini,0,31,0.82
symbolic,o3-mini,0,46,0.62
symbolic,o3-mini,0,61,0.34
symbolic,o3-mini,0,76,0.28
symbolic,o3-mini,0,91,0.22
symbolic,o3-mini,0,106,0.12
symbolic,o3-mini,0,121,0.1
symbolic,o3-mini,0,136,0.14
symbolic,o3-mini,0,151,0.16
symbolic,o3-mini,0,166,0.08
symbolic,o3-mini,0,181,0.06
symbolic,o3-mini,0,196,0.0
symbolic,o3-mini,0,211,0.04
symbolic,o3-mini,0,226,0.04
realistic_Hard,mistral-large-2411,0,2,0.8672
realistic_Hard,mistral-large-2411,0,4,0.9141
realistic_Hard,mistral-large-2411,0,6,0.8672
realistic_Hard,mistral-large-2411,0,8,0.8594
realistic_Hard,mistral-large-2411,0,10,0.7578
realistic_Hard,mistral-large-2411,0,12,0.6875
realistic_Hard,mistral-large-2411,0,14,0.7812
realistic_Hard,mistral-large-2411,0,16,0.7266
realistic_Hard,mistral-large-2411,0,18,0.7109
realistic_Hard,mistral-large-2411,0,20,0.6172
realistic_Hard,mistral-large-2411,0,22,0.5156
realistic_Hard,mistral-large-2411,0,24,0.4646
realistic_Hard,mistral-large-2411,0,26,0.4453
realistic_Hard,mistral-large-2411,0,28,0.4252
realistic_Hard,mistral-large-2411,0,30,0.3281
realistic_Hard,mistral-large-2411,0,35,0.230769
realistic_Hard,mistral-large-2411,0,40,0.16667
realistic_Hard,mistral-large-2411,0,50,0.0714
realistic_Hard,mistral-large-2411,0,55,0.0938
realistic_Hard,mistral-large-2411,0,60,0.0543
realistic_Hard,mistral-large-2411,8000,2,0.7109
realistic_Hard,mistral-large-2411,8000,6,0.7734
realistic_Hard,mistral-large-2411,8000,10,0.5391
realistic_Hard,mistral-large-2411,8000,14,0.5859
realistic_Hard,mistral-large-2411,8000,18,0.4219
realistic_Hard,mistral-large-2411,8000,22,0.3828
realistic_Hard,mistral-large-2411,8000,26,0.3828
realistic_Hard,mistral-large-2411,8000,30,0.4375
realistic_Hard,mistral-large-2411,16000,2,0.6562
realistic_Hard,mistral-large-2411,16000,6,0.6094
realistic_Hard,mistral-large-2411,16000,10,0.3984
realistic_Hard,mistral-large-2411,16000,14,0.2266
realistic_Hard,mistral-large-2411,16000,18,0.1406
realistic_Hard,mistral-large-2411,16000,22,0.0938
realistic_Hard,mistral-large-2411,16000,26,0.0859
realistic_Hard,mistral-large-2411,16000,30,0.0703
realistic_Hard,mistral-large-2411,32000,2,0.4688
realistic_Hard,mistral-large-2411,32000,6,0.3516
realistic_Hard,mistral-large-2411,32000,10,0.1653
realistic_Hard,mistral-large-2411,32000,14,0.0787
realistic_Hard,mistral-large-2411,32000,18,0.0859
realistic_Hard,mistral-large-2411,32000,22,0.0859
realistic_Hard,mistral-large-2411,32000,26,0.0078
realistic_Hard,mistral-large-2411,32000,30,0.0234
realistic_Hard,llama-3.1-70b-instruct,0,2,0.84
realistic_Hard,llama-3.1-70b-instruct,0,3,0.9
realistic_Hard,llama-3.1-70b-instruct,0,4,0.815
realistic_Hard,llama-3.1-70b-instruct,0,5,0.73
realistic_Hard,llama-3.1-70b-instruct,0,6,0.735
realistic_Hard,llama-3.1-70b-instruct,0,7,0.66
realistic_Hard,llama-3.1-70b-instruct,0,8,0.655
realistic_Hard,llama-3.1-70b-instruct,0,9,0.65
realistic_Hard,llama-3.1-70b-instruct,0,10,0.64
realistic_Hard,llama-3.1-70b-instruct,0,11,0.52
realistic_Hard,llama-3.1-70b-instruct,0,12,0.55
realistic_Hard,llama-3.1-70b-instruct,0,13,0.415
realistic_Hard,llama-3.1-70b-instruct,0,14,0.5
realistic_Hard,llama-3.1-70b-instruct,0,15,0.49
realistic_Hard,llama-3.1-70b-instruct,0,16,0.4
realistic_Hard,llama-3.1-70b-instruct,0,17,0.345
realistic_Hard,llama-3.1-70b-instruct,0,18,0.41
realistic_Hard,llama-3.1-70b-instruct,0,19,0.335
realistic_Hard,llama-3.1-70b-instruct,0,20,0.325
realistic_Hard,llama-3.1-70b-instruct,0,21,0.235
realistic_Hard,llama-3.1-70b-instruct,0,22,0.2
realistic_Hard,llama-3.1-70b-instruct,0,23,0.165
realistic_Hard,llama-3.1-70b-instruct,0,24,0.185
realistic_Hard,llama-3.1-70b-instruct,0,25,0.2
realistic_Hard,llama-3.1-70b-instruct,0,26,0.115
realistic_Hard,llama-3.1-70b-instruct,0,27,0.15
realistic_Hard,llama-3.1-70b-instruct,0,28,0.1
realistic_Hard,llama-3.1-70b-instruct,0,29,0.17
realistic_Hard,llama-3.1-70b-instruct,0,30,0.075
realistic_Hard,llama-3.1-70b-instruct,8000,2,0.77
realistic_Hard,llama-3.1-70b-instruct,8000,4,0.705
realistic_Hard,llama-3.1-70b-instruct,8000,6,0.635
realistic_Hard,llama-3.1-70b-instruct,8000,8,0.475
realistic_Hard,llama-3.1-70b-instruct,8000,10,0.385
realistic_Hard,llama-3.1-70b-instruct,8000,12,0.275
realistic_Hard,llama-3.1-70b-instruct,8000,14,0.175
realistic_Hard,llama-3.1-70b-instruct,8000,16,0.08
realistic_Hard,llama-3.1-70b-instruct,8000,18,0.03
realistic_Hard,llama-3.1-70b-instruct,8000,20,0.02
realistic_Hard,llama-3.1-70b-instruct,8000,22,0.005
realistic_Hard,llama-3.1-70b-instruct,8000,24,0.0
realistic_Hard,llama-3.1-70b-instruct,8000,26,0.0
realistic_Hard,llama-3.1-70b-instruct,8000,28,0.0
realistic_Hard,llama-3.1-70b-instruct,8000,30,0.0
realistic_Hard,llama-3.1-70b-instruct,16000,2,0.76
realistic_Hard,llama-3.1-70b-instruct,16000,4,0.615
realistic_Hard,llama-3.1-70b-instruct,16000,6,0.56
realistic_Hard,llama-3.1-70b-instruct,16000,8,0.385
realistic_Hard,llama-3.1-70b-instruct,16000,10,0.245
realistic_Hard,llama-3.1-70b-instruct,16000,12,0.18
realistic_Hard,llama-3.1-70b-instruct,16000,14,0.1
realistic_Hard,llama-3.1-70b-instruct,16000,16,0.035
realistic_Hard,llama-3.1-70b-instruct,16000,18,0.03
realistic_Hard,llama-3.1-70b-instruct,16000,20,0.02
realistic_Hard,llama-3.1-70b-instruct,16000,22,0.015
realistic_Hard,llama-3.1-70b-instruct,16000,24,0.025
realistic_Hard,llama-3.1-70b-instruct,16000,26,0.01
realistic_Hard,llama-3.1-70b-instruct,16000,28,0.015
realistic_Hard,llama-3.1-70b-instruct,16000,30,0.025
realistic_Hard,llama-3.1-70b-instruct,32000,2,0.725
realistic_Hard,llama-3.1-70b-instruct,32000,4,0.575
realistic_Hard,llama-3.1-70b-instruct,32000,6,0.445
realistic_Hard,llama-3.1-70b-instruct,32000,8,0.39
realistic_Hard,llama-3.1-70b-instruct,32000,10,0.12
realistic_Hard,llama-3.1-70b-instruct,32000,12,0.08
realistic_Hard,llama-3.1-70b-instruct,32000,14,0.075
realistic_Hard,llama-3.1-70b-instruct,32000,16,0.075
realistic_Hard,llama-3.1-70b-instruct,32000,18,0.045
realistic_Hard,llama-3.1-70b-instruct,32000,20,0.015
realistic_Hard,llama-3.1-70b-instruct,32000,22,0.03
realistic_Hard,llama-3.1-70b-instruct,32000,24,0.01
realistic_Hard,llama-3.1-70b-instruct,32000,26,0.015
realistic_Hard,llama-3.1-70b-instruct,32000,28,0.015
realistic_Hard,llama-3.1-70b-instruct,32000,30,0.025
realistic_Medium,llama-3.1-70b-instruct,0,2,0.74
realistic_Medium,llama-3.1-70b-instruct,0,3,0.725
realistic_Medium,llama-3.1-70b-instruct,0,4,0.9
realistic_Medium,llama-3.1-70b-instruct,0,5,0.865
realistic_Medium,llama-3.1-70b-instruct,0,6,0.935
realistic_Medium,llama-3.1-70b-instruct,0,7,0.905
realistic_Medium,llama-3.1-70b-instruct,0,8,0.795
realistic_Medium,llama-3.1-70b-instruct,0,9,0.805
realistic_Medium,llama-3.1-70b-instruct,0,10,0.69
realistic_Medium,llama-3.1-70b-instruct,0,11,0.7
realistic_Medium,llama-3.1-70b-instruct,0,12,0.625
realistic_Medium,llama-3.1-70b-instruct,0,13,0.575
realistic_Medium,llama-3.1-70b-instruct,0,14,0.565
realistic_Medium,llama-3.1-70b-instruct,0,15,0.58
realistic_Medium,llama-3.1-70b-instruct,0,16,0.38
realistic_Medium,llama-3.1-70b-instruct,0,17,0.465
realistic_Medium,llama-3.1-70b-instruct,0,18,0.42
realistic_Medium,llama-3.1-70b-instruct,0,19,0.355
realistic_Medium,llama-3.1-70b-instruct,0,20,0.415
realistic_Medium,llama-3.1-70b-instruct,0,21,0.335
realistic_Medium,llama-3.1-70b-instruct,0,22,0.36
realistic_Medium,llama-3.1-70b-instruct,0,23,0.32
realistic_Medium,llama-3.1-70b-instruct,0,24,0.305
realistic_Medium,llama-3.1-70b-instruct,0,25,0.385
realistic_Medium,llama-3.1-70b-instruct,0,26,0.265
realistic_Medium,llama-3.1-70b-instruct,0,27,0.305
realistic_Medium,llama-3.1-70b-instruct,0,28,0.255
realistic_Medium,llama-3.1-70b-instruct,0,29,0.175
realistic_Medium,llama-3.1-70b-instruct,0,30,0.18
realistic_Medium,llama-3.1-70b-instruct,0,35,0.125
realistic_Medium,llama-3.1-70b-instruct,0,40,0.08125
realistic_Medium,llama-3.1-70b-instruct,0,45,0.0625
realistic_Medium,llama-3.1-70b-instruct,8000,2,0.48
realistic_Medium,llama-3.1-70b-instruct,8000,4,0.725
realistic_Medium,llama-3.1-70b-instruct,8000,6,0.745
realistic_Medium,llama-3.1-70b-instruct,8000,8,0.53
realistic_Medium,llama-3.1-70b-instruct,8000,10,0.22
realistic_Medium,llama-3.1-70b-instruct,8000,12,0.165
realistic_Medium,llama-3.1-70b-instruct,8000,14,0.11
realistic_Medium,llama-3.1-70b-instruct,8000,16,0.055
realistic_Medium,llama-3.1-70b-instruct,8000,18,0.035
realistic_Medium,llama-3.1-70b-instruct,8000,20,0.01
realistic_Medium,llama-3.1-70b-instruct,8000,22,0.005
realistic_Medium,llama-3.1-70b-instruct,8000,24,0.015
realistic_Medium,llama-3.1-70b-instruct,8000,26,0.0
realistic_Medium,llama-3.1-70b-instruct,8000,28,0.005
realistic_Medium,llama-3.1-70b-instruct,8000,30,0.005
realistic_Medium,llama-3.1-70b-instruct,16000,2,0.325
realistic_Medium,llama-3.1-70b-instruct,16000,4,0.68
realistic_Medium,llama-3.1-70b-instruct,16000,6,0.62
realistic_Medium,llama-3.1-70b-instruct,16000,8,0.39
realistic_Medium,llama-3.1-70b-instruct,16000,10,0.15
realistic_Medium,llama-3.1-70b-instruct,16000,12,0.12
realistic_Medium,llama-3.1-70b-instruct,16000,14,0.085
realistic_Medium,llama-3.1-70b-instruct,16000,16,0.03
realistic_Medium,llama-3.1-70b-instruct,16000,18,0.015
realistic_Medium,llama-3.1-70b-instruct,16000,20,0.015
realistic_Medium,llama-3.1-70b-instruct,16000,22,0.01
realistic_Medium,llama-3.1-70b-instruct,16000,24,0.005
realistic_Medium,llama-3.1-70b-instruct,16000,26,0.0
realistic_Medium,llama-3.1-70b-instruct,16000,28,0.01
realistic_Medium,llama-3.1-70b-instruct,16000,30,0.005
realistic_Medium,llama-3.1-70b-instruct,32000,2,0.325
realistic_Medium,llama-3.1-70b-instruct,32000,4,0.68
realistic_Medium,llama-3.1-70b-instruct,32000,6,0.62
realistic_Medium,llama-3.1-70b-instruct,32000,8,0.39
realistic_Medium,llama-3.1-70b-instruct,32000,10,0.15
realistic_Medium,llama-3.1-70b-instruct,32000,12,0.12
realistic_Medium,llama-3.1-70b-instruct,32000,14,0.065
realistic_Medium,llama-3.1-70b-instruct,32000,16,0.02
realistic_Medium,llama-3.1-70b-instruct,32000,18,0.005
realistic_Medium,llama-3.1-70b-instruct,32000,20,0.005
realistic_Medium,llama-3.1-70b-instruct,32000,22,0.0
realistic_Medium,llama-3.1-70b-instruct,32000,24,0.005
realistic_Medium,llama-3.1-70b-instruct,32000,26,0.035
realistic_Medium,llama-3.1-70b-instruct,32000,28,0.025
realistic_Medium,llama-3.1-70b-instruct,32000,30,0.02
realistic_Medium,claude-3.5-haiku,0,2,0.5859
realistic_Medium,claude-3.5-haiku,0,6,0.7266
realistic_Medium,claude-3.5-haiku,0,10,0.5547
realistic_Medium,claude-3.5-haiku,0,14,0.4688
realistic_Medium,claude-3.5-haiku,0,18,0.3047
realistic_Medium,claude-3.5-haiku,0,22,0.1719
realistic_Medium,claude-3.5-haiku,0,26,0.0859
realistic_Medium,claude-3.5-haiku,0,30,0.0547
realistic_Hard,claude-3.5-haiku,0,2,0.6484
realistic_Hard,claude-3.5-haiku,0,6,0.7031
realistic_Hard,claude-3.5-haiku,0,10,0.4844
realistic_Hard,claude-3.5-haiku,0,14,0.2656
realistic_Hard,claude-3.5-haiku,0,18,0.1094
realistic_Hard,claude-3.5-haiku,0,22,0.0312
realistic_Hard,claude-3.5-haiku,0,26,0.0
realistic_Hard,claude-3.5-haiku,0,30,0.0859
symbolic,gemini-1.5-flash-002,0,1,0.99
symbolic,gemini-1.5-flash-002,0,3,0.98
symbolic,gemini-1.5-flash-002,0,5,0.89
symbolic,gemini-1.5-flash-002,0,7,0.85
symbolic,gemini-1.5-flash-002,0,9,0.83
symbolic,gemini-1.5-flash-002,0,11,0.75
symbolic,gemini-1.5-flash-002,0,13,0.63
symbolic,gemini-1.5-flash-002,0,15,0.59
symbolic,gemini-1.5-flash-002,0,17,0.65
symbolic,gemini-1.5-flash-002,0,19,0.53
symbolic,gemini-1.5-flash-002,0,21,0.41
symbolic,gemini-1.5-flash-002,0,23,0.3
symbolic,gemini-1.5-flash-002,0,25,0.35
symbolic,gemini-1.5-flash-002,0,27,0.32
symbolic,gemini-1.5-flash-002,0,29,0.28
symbolic,gemini-1.5-flash-002,0,31,0.2
symbolic,gemini-1.5-flash-002,0,33,0.18
symbolic,gemini-1.5-flash-002,0,35,0.08
symbolic,gemini-1.5-flash-002,0,37,0.14
symbolic,gemini-1.5-flash-002,0,39,0.08
symbolic,gemini-1.5-flash-002,0,41,0.08
symbolic,gemini-1.5-flash-002,0,43,0.03
symbolic,gemini-1.5-flash-002,0,45,0.04
symbolic,gemini-1.5-flash-002,0,47,0.05
symbolic,gemini-1.5-flash-002,0,49,0.05
symbolic,gemini-1.5-flash-002,0,51,0.03
symbolic,gemini-1.5-flash-002,0,53,0.01
symbolic,gemini-1.5-flash-002,0,55,0.02
symbolic,gemini-1.5-flash-002,0,57,0.0
symbolic,gemini-1.5-flash-002,0,59,0.01
symbolic,gemini-1.5-flash-002,8000,1,0.9
symbolic,gemini-1.5-flash-002,8000,2,0.59
symbolic,gemini-1.5-flash-002,8000,3,0.38
symbolic,gemini-1.5-flash-002,8000,4,0.32
symbolic,gemini-1.5-flash-002,8000,5,0.27
symbolic,gemini-1.5-flash-002,8000,6,0.17
symbolic,gemini-1.5-flash-002,8000,7,0.11
symbolic,gemini-1.5-flash-002,8000,8,0.14
symbolic,gemini-1.5-flash-002,8000,9,0.06
symbolic,gemini-1.5-flash-002,8000,10,0.03
symbolic,gemini-1.5-flash-002,8000,11,0.09
symbolic,gemini-1.5-flash-002,8000,12,0.03
symbolic,gemini-1.5-flash-002,8000,13,0.06
symbolic,gemini-1.5-flash-002,8000,14,0.05
symbolic,gemini-1.5-flash-002,8000,15,0.02
symbolic,gemini-1.5-flash-002,8000,16,0.01
symbolic,gemini-1.5-flash-002,8000,17,0.01
symbolic,gemini-1.5-flash-002,8000,18,0.0
symbolic,gemini-1.5-flash-002,8000,19,0.01
symbolic,gemini-1.5-flash-002,16000,1,0.8
symbolic,gemini-1.5-flash-002,16000,2,0.54
symbolic,gemini-1.5-flash-002,16000,3,0.3
symbolic,gemini-1.5-flash-002,16000,4,0.26
symbolic,gemini-1.5-flash-002,16000,5,0.14
symbolic,gemini-1.5-flash-002,16000,6,0.1
symbolic,gemini-1.5-flash-002,16000,7,0.1
symbolic,gemini-1.5-flash-002,16000,8,0.04
symbolic,gemini-1.5-flash-002,16000,9,0.08
symbolic,gemini-1.5-flash-002,16000,10,0.04
symbolic,gemini-1.5-flash-002,16000,11,0.04
symbolic,gemini-1.5-flash-002,16000,12,0.0
symbolic,gemini-1.5-flash-002,16000,13,0.02
symbolic,gemini-1.5-flash-002,32000,1,0.64
symbolic,gemini-1.5-flash-002,32000,2,0.36
symbolic,gemini-1.5-flash-002,32000,3,0.3
symbolic,gemini-1.5-flash-002,32000,4,0.18
symbolic,gemini-1.5-flash-002,32000,5,0.1
symbolic,gemini-1.5-flash-002,32000,6,0.12
symbolic,gemini-1.5-flash-002,32000,7,0.06
symbolic,gemini-1.5-flash-002,32000,8,0.02
symbolic,gemini-1.5-flash-002,32000,9,0.02
symbolic,qwen-2.5-7b-instruct,0,1,0.984
symbolic,qwen-2.5-7b-instruct,0,2,0.97
symbolic,qwen-2.5-7b-instruct,0,3,0.829
symbolic,qwen-2.5-7b-instruct,0,4,0.765
symbolic,qwen-2.5-7b-instruct,0,5,0.66
symbolic,qwen-2.5-7b-instruct,0,6,0.595
symbolic,qwen-2.5-7b-instruct,0,7,0.527
symbolic,qwen-2.5-7b-instruct,0,8,0.438
symbolic,qwen-2.5-7b-instruct,0,9,0.37
symbolic,qwen-2.5-7b-instruct,0,10,0.331
symbolic,qwen-2.5-7b-instruct,0,11,0.257
symbolic,qwen-2.5-7b-instruct,0,12,0.238
symbolic,qwen-2.5-7b-instruct,0,13,0.21
symbolic,qwen-2.5-7b-instruct,0,14,0.183
symbolic,qwen-2.5-7b-instruct,0,15,0.155
symbolic,qwen-2.5-7b-instruct,0,16,0.104
symbolic,qwen-2.5-7b-instruct,0,17,0.083
symbolic,qwen-2.5-7b-instruct,0,18,0.079
symbolic,qwen-2.5-7b-instruct,0,19,0.087
symbolic,qwen-2.5-7b-instruct,0,20,0.057
symbolic,qwen-2.5-7b-instruct,0,21,0.064
symbolic,qwen-2.5-7b-instruct,0,22,0.041
symbolic,qwen-2.5-7b-instruct,0,23,0.043
symbolic,qwen-2.5-7b-instruct,0,24,0.035
symbolic,qwen-2.5-7b-instruct,0,25,0.03
symbolic,qwen-2.5-7b-instruct,0,26,0.021
symbolic,qwen-2.5-7b-instruct,0,27,0.026
symbolic,qwen-2.5-7b-instruct,0,28,0.027
symbolic,qwen-2.5-7b-instruct,0,29,0.023
symbolic,qwen-2.5-7b-instruct,0,30,0.018
symbolic,qwen-2.5-7b-instruct,0,31,0.017
symbolic,qwen-2.5-7b-instruct,0,32,0.009
symbolic,qwen-2.5-7b-instruct,0,33,0.014
symbolic,qwen-2.5-7b-instruct,0,34,0.019
symbolic,qwen-2.5-7b-instruct,0,35,0.01
symbolic,qwen-2.5-7b-instruct,0,36,0.012
symbolic,qwen-2.5-7b-instruct,0,37,0.013
symbolic,qwen-2.5-7b-instruct,0,38,0.006
symbolic,qwen-2.5-7b-instruct,0,39,0.006
symbolic,qwen-2.5-7b-instruct,0,40,0.011
symbolic,qwen-2.5-7b-instruct,8000,1,0.43
symbolic,qwen-2.5-7b-instruct,8000,2,0.14
symbolic,qwen-2.5-7b-instruct,8000,3,0.07
symbolic,qwen-2.5-7b-instruct,8000,4,0.02
symbolic,qwen-2.5-7b-instruct,8000,5,0.01
symbolic,qwen-2.5-7b-instruct,16000,1,0.1
symbolic,qwen-2.5-7b-instruct,16000,2,0.02
symbolic,qwen-2.5-7b-instruct,16000,3,0.02
symbolic,gpt-4o-mini,0,1,0.97
symbolic,gpt-4o-mini,0,3,0.99
symbolic,gpt-4o-mini,0,5,0.92
symbolic,gpt-4o-mini,0,7,0.85
symbolic,gpt-4o-mini,0,9,0.76
symbolic,gpt-4o-mini,0,11,0.64
symbolic,gpt-4o-mini,0,13,0.52
symbolic,gpt-4o-mini,0,15,0.39
symbolic,gpt-4o-mini,0,17,0.36
symbolic,gpt-4o-mini,0,19,0.22
symbolic,gpt-4o-mini,0,21,0.16
symbolic,gpt-4o-mini,0,23,0.13
symbolic,gpt-4o-mini,0,25,0.11
symbolic,gpt-4o-mini,0,27,0.09
symbolic,gpt-4o-mini,0,29,0.07
symbolic,gpt-4o-mini,0,31,0.06
symbolic,gpt-4o-mini,0,33,0.05
symbolic,gpt-4o-mini,0,35,0.03
symbolic,gpt-4o-mini,0,37,0.03
symbolic,gpt-4o-mini,0,39,0.0
symbolic,gpt-4o-mini,0,41,0.03
symbolic,gpt-4o-mini,0,43,0.0
symbolic,gpt-4o-mini,0,45,0.03
symbolic,gpt-4o-mini,0,47,0.01
symbolic,gpt-4o-mini,0,49,0.0
symbolic,gpt-4o-mini,0,51,0.01
symbolic,gpt-4o-mini,0,53,0.0
symbolic,gpt-4o-mini,0,55,0.0
symbolic,gpt-4o-mini,0,57,0.0
symbolic,gpt-4o-mini,0,59,0.0
symbolic,gpt-4o-mini,8000,1,0.8
symbolic,gpt-4o-mini,8000,2,0.3
symbolic,gpt-4o-mini,8000,3,0.14
symbolic,gpt-4o-mini,8000,4,0.07
symbolic,gpt-4o-mini,8000,5,0.06
symbolic,gpt-4o-mini,8000,6,0.03
symbolic,gpt-4o-mini,8000,7,0.02
symbolic,gpt-4o-mini,8000,8,0.01
symbolic,gpt-4o-mini,8000,9,0.0
symbolic,gpt-4o-mini,8000,10,0.0
symbolic,gpt-4o-mini,8000,11,0.0
symbolic,gpt-4o-mini,16000,1,0.64
symbolic,gpt-4o-mini,16000,2,0.32
symbolic,gpt-4o-mini,16000,3,0.12
symbolic,gpt-4o-mini,16000,4,0.01
symbolic,gpt-4o-mini,16000,5,0.07
symbolic,gpt-4o-mini,16000,6,0.02
symbolic,gpt-4o-mini,16000,7,0.04
symbolic,gpt-4o-mini,16000,8,0.0
symbolic,gpt-4o-mini,32000,1,0.41
symbolic,gpt-4o-mini,32000,2,0.2
symbolic,gpt-4o-mini,32000,3,0.09
symbolic,gpt-4o-mini,32000,4,0.05
symbolic,gpt-4o-mini,32000,5,0.01
symbolic,gpt-4o-mini,32000,6,0.04
symbolic,gpt-4o-mini,32000,7,0.02
symbolic,llama-3.1-70b-instruct,0,1,0.99
symbolic,llama-3.1-70b-instruct,0,3,0.97
symbolic,llama-3.1-70b-instruct,0,5,0.84
symbolic,llama-3.1-70b-instruct,0,7,0.84
symbolic,llama-3.1-70b-instruct,0,9,0.7
symbolic,llama-3.1-70b-instruct,0,11,0.65
symbolic,llama-3.1-70b-instruct,0,13,0.53
symbolic,llama-3.1-70b-instruct,0,15,0.45
symbolic,llama-3.1-70b-instruct,0,17,0.47
symbolic,llama-3.1-70b-instruct,0,19,0.41
symbolic,llama-3.1-70b-instruct,0,21,0.31
symbolic,llama-3.1-70b-instruct,0,23,0.31
symbolic,llama-3.1-70b-instruct,0,25,0.26
symbolic,llama-3.1-70b-instruct,0,27,0.19
symbolic,llama-3.1-70b-instruct,0,29,0.23
symbolic,llama-3.1-70b-instruct,0,31,0.13
symbolic,llama-3.1-70b-instruct,0,33,0.25
symbolic,llama-3.1-70b-instruct,0,35,0.08
symbolic,llama-3.1-70b-instruct,0,37,0.11
symbolic,llama-3.1-70b-instruct,0,39,0.07
symbolic,llama-3.1-70b-instruct,0,41,0.08
symbolic,llama-3.1-70b-instruct,0,43,0.06
symbolic,llama-3.1-70b-instruct,0,45,0.09
symbolic,llama-3.1-70b-instruct,0,47,0.07
symbolic,llama-3.1-70b-instruct,0,49,0.06
symbolic,llama-3.1-70b-instruct,0,51,0.06
symbolic,llama-3.1-70b-instruct,0,53,0.06
symbolic,llama-3.1-70b-instruct,0,55,0.02
symbolic,llama-3.1-70b-instruct,0,57,0.04
symbolic,llama-3.1-70b-instruct,0,59,0.02
symbolic,llama-3.1-70b-instruct,8000,1,0.96
symbolic,llama-3.1-70b-instruct,8000,2,0.61
symbolic,llama-3.1-70b-instruct,8000,3,0.39
symbolic,llama-3.1-70b-instruct,8000,4,0.26
symbolic,llama-3.1-70b-instruct,8000,5,0.16
symbolic,llama-3.1-70b-instruct,8000,6,0.17
symbolic,llama-3.1-70b-instruct,8000,7,0.08
symbolic,llama-3.1-70b-instruct,8000,8,0.07
symbolic,llama-3.1-70b-instruct,8000,9,0.08
symbolic,llama-3.1-70b-instruct,8000,10,0.01
symbolic,llama-3.1-70b-instruct,16000,1,0.92
symbolic,llama-3.1-70b-instruct,16000,2,0.57
symbolic,llama-3.1-70b-instruct,16000,3,0.37
symbolic,llama-3.1-70b-instruct,16000,4,0.2
symbolic,llama-3.1-70b-instruct,16000,5,0.12
symbolic,llama-3.1-70b-instruct,16000,6,0.1
symbolic,llama-3.1-70b-instruct,16000,7,0.06
symbolic,llama-3.1-70b-instruct,16000,8,0.06
symbolic,llama-3.1-70b-instruct,16000,9,0.04
symbolic,llama-3.1-70b-instruct,16000,10,0.02
symbolic,llama-3.1-70b-instruct,32000,1,0.91
symbolic,llama-3.1-70b-instruct,32000,2,0.51
symbolic,llama-3.1-70b-instruct,32000,3,0.21
symbolic,llama-3.1-70b-instruct,32000,4,0.13
symbolic,llama-3.1-70b-instruct,32000,5,0.12
symbolic,llama-3.1-70b-instruct,32000,6,0.03
symbolic,llama-3.1-70b-instruct,32000,7,0.05
symbolic,llama-3.1-70b-instruct,32000,8,0.0
symbolic,llama-3.1-70b-instruct,32000,9,0.03
symbolic,llama-3.1-70b-instruct,32000,10,0.03
realistic_Medium,minimax-text-01,0,2,0.7734
realistic_Medium,minimax-text-01,0,3,0.7656
realistic_Medium,minimax-text-01,0,4,0.9062
realistic_Medium,minimax-text-01,0,5,0.8906
realistic_Medium,minimax-text-01,0,6,0.8828
realistic_Medium,minimax-text-01,0,7,0.8828
realistic_Medium,minimax-text-01,0,8,0.8203
realistic_Medium,minimax-text-01,0,9,0.8672
realistic_Medium,minimax-text-01,0,10,0.6484
realistic_Medium,minimax-text-01,0,11,0.7969
realistic_Medium,minimax-text-01,0,12,0.6328
realistic_Medium,minimax-text-01,0,13,0.6016
realistic_Medium,minimax-text-01,0,14,0.6406
realistic_Medium,minimax-text-01,0,15,0.6562
realistic_Medium,minimax-text-01,0,16,0.4688
realistic_Medium,minimax-text-01,0,17,0.3906
realistic_Medium,minimax-text-01,0,18,0.4453
realistic_Medium,minimax-text-01,0,19,0.4844
realistic_Medium,minimax-text-01,0,20,0.4609
realistic_Medium,minimax-text-01,0,21,0.3516
realistic_Medium,minimax-text-01,0,22,0.375
realistic_Medium,minimax-text-01,0,23,0.3594
realistic_Medium,minimax-text-01,0,24,0.3359
realistic_Medium,minimax-text-01,0,25,0.2656
realistic_Medium,minimax-text-01,0,26,0.25
realistic_Medium,minimax-text-01,0,27,0.2266
realistic_Medium,minimax-text-01,0,28,0.2031
realistic_Medium,minimax-text-01,0,29,0.1719
realistic_Medium,minimax-text-01,0,30,0.1641
realistic_Medium,minimax-text-01,0,35,0.163462
realistic_Medium,minimax-text-01,0,40,0.0865385
realistic_Medium,minimax-text-01,0,45,0.0865385
realistic_Medium,minimax-text-01,8000,2,0.4531
realistic_Medium,minimax-text-01,8000,4,0.6406
realistic_Medium,minimax-text-01,8000,6,0.5469
realistic_Medium,minimax-text-01,8000,8,0.4531
realistic_Medium,minimax-text-01,8000,10,0.2891
realistic_Medium,minimax-text-01,8000,12,0.1797
realistic_Medium,minimax-text-01,8000,14,0.1328
realistic_Medium,minimax-text-01,8000,16,0.1328
realistic_Medium,minimax-text-01,8000,18,0.0938
realistic_Medium,minimax-text-01,8000,20,0.0781
realistic_Medium,minimax-text-01,8000,22,0.0859
realistic_Medium,minimax-text-01,8000,24,0.0781
realistic_Medium,minimax-text-01,8000,26,0.0547
realistic_Medium,minimax-text-01,8000,28,0.0469
realistic_Medium,minimax-text-01,8000,30,0.0547
realistic_Medium,minimax-text-01,16000,2,0.4062
realistic_Medium,minimax-text-01,16000,4,0.6562
realistic_Medium,minimax-text-01,16000,6,0.5391
realistic_Medium,minimax-text-01,16000,8,0.2734
realistic_Medium,minimax-text-01,16000,10,0.1094
realistic_Medium,minimax-text-01,16000,12,0.125
realistic_Medium,minimax-text-01,16000,14,0.1016
realistic_Medium,minimax-text-01,16000,16,0.0625
realistic_Medium,minimax-text-01,16000,18,0.0547
realistic_Medium,minimax-text-01,16000,20,0.0625
realistic_Medium,minimax-text-01,16000,22,0.0234
realistic_Medium,minimax-text-01,16000,24,0.0391
realistic_Medium,minimax-text-01,16000,26,0.0547
realistic_Medium,minimax-text-01,16000,28,0.0391
realistic_Medium,minimax-text-01,16000,30,0.0234
realistic_Medium,minimax-text-01,32000,2,0.3672
realistic_Medium,minimax-text-01,32000,4,0.5391
realistic_Medium,minimax-text-01,32000,6,0.5625
realistic_Medium,minimax-text-01,32000,8,0.3125
realistic_Medium,minimax-text-01,32000,10,0.1406
realistic_Medium,minimax-text-01,32000,12,0.1094
realistic_Medium,minimax-text-01,32000,14,0.1094
realistic_Medium,minimax-text-01,32000,16,0.0391
realistic_Medium,minimax-text-01,32000,18,0.1016
realistic_Medium,minimax-text-01,32000,20,0.0547
realistic_Medium,minimax-text-01,32000,22,0.0703
realistic_Medium,minimax-text-01,32000,24,0.0703
realistic_Medium,minimax-text-01,32000,26,0.0391
realistic_Medium,minimax-text-01,32000,28,0.0469
realistic_Hard,minimax-text-01,0,2,0.8047
realistic_Hard,minimax-text-01,0,3,0.8281
realistic_Hard,minimax-text-01,0,4,0.875
realistic_Hard,minimax-text-01,0,5,0.8125
realistic_Hard,minimax-text-01,0,6,0.8125
realistic_Hard,minimax-text-01,0,7,0.7031
realistic_Hard,minimax-text-01,0,8,0.6875
realistic_Hard,minimax-text-01,0,9,0.7266
realistic_Hard,minimax-text-01,0,10,0.6875
realistic_Hard,minimax-text-01,0,11,0.5781
realistic_Hard,minimax-text-01,0,12,0.4922
realistic_Hard,minimax-text-01,0,13,0.5156
realistic_Hard,minimax-text-01,0,14,0.4766
realistic_Hard,minimax-text-01,0,15,0.3516
realistic_Hard,minimax-text-01,0,16,0.4375
realistic_Hard,minimax-text-01,0,17,0.3516
realistic_Hard,minimax-text-01,0,18,0.3281
realistic_Hard,minimax-text-01,0,19,0.2734
realistic_Hard,minimax-text-01,0,20,0.3125
realistic_Hard,minimax-text-01,0,21,0.1484
realistic_Hard,minimax-text-01,0,22,0.1328
realistic_Hard,minimax-text-01,0,23,0.1484
realistic_Hard,minimax-text-01,0,24,0.1406
realistic_Hard,minimax-text-01,0,25,0.0938
realistic_Hard,minimax-text-01,0,26,0.0703
realistic_Hard,minimax-text-01,0,27,0.1016
realistic_Hard,minimax-text-01,0,28,0.1094
realistic_Hard,minimax-text-01,0,29,0.1562
realistic_Hard,minimax-text-01,0,30,0.0625
realistic_Hard,minimax-text-01,8000,2,0.7734
realistic_Hard,minimax-text-01,8000,4,0.6484
realistic_Hard,minimax-text-01,8000,6,0.5469
realistic_Hard,minimax-text-01,8000,8,0.4375
realistic_Hard,minimax-text-01,8000,10,0.2969
realistic_Hard,minimax-text-01,8000,12,0.1953
realistic_Hard,minimax-text-01,8000,14,0.1406
realistic_Hard,minimax-text-01,8000,16,0.1953
realistic_Hard,minimax-text-01,8000,18,0.1172
realistic_Hard,minimax-text-01,8000,20,0.0781
realistic_Hard,minimax-text-01,8000,22,0.1016
realistic_Hard,minimax-text-01,8000,24,0.0469
realistic_Hard,minimax-text-01,8000,26,0.0547
realistic_Hard,minimax-text-01,8000,28,0.0703
realistic_Hard,minimax-text-01,8000,30,0.0391
realistic_Hard,minimax-text-01,16000,2,0.6094
realistic_Hard,minimax-text-01,16000,4,0.5391
realistic_Hard,minimax-text-01,16000,6,0.4609
realistic_Hard,minimax-text-01,16000,8,0.3203
realistic_Hard,minimax-text-01,16000,10,0.1172
realistic_Hard,minimax-text-01,16000,12,0.1094
realistic_Hard,minimax-text-01,16000,14,0.0859
realistic_Hard,minimax-text-01,16000,16,0.0625
realistic_Hard,minimax-text-01,16000,18,0.0234
realistic_Hard,minimax-text-01,16000,20,0.0781
realistic_Hard,minimax-text-01,16000,22,0.0547
realistic_Hard,minimax-text-01,16000,24,0.0547
realistic_Hard,minimax-text-01,16000,26,0.0469
realistic_Hard,minimax-text-01,16000,28,0.0234
realistic_Hard,minimax-text-01,16000,30,0.0234
realistic_Hard,minimax-text-01,32000,2,0.5547
realistic_Hard,minimax-text-01,32000,4,0.4922
realistic_Hard,minimax-text-01,32000,6,0.3594
realistic_Hard,minimax-text-01,32000,8,0.1875
realistic_Hard,minimax-text-01,32000,10,0.1406
realistic_Hard,minimax-text-01,32000,12,0.0781
realistic_Hard,minimax-text-01,32000,14,0.0625
realistic_Hard,minimax-text-01,32000,16,0.0547
realistic_Hard,minimax-text-01,32000,18,0.0781
realistic_Hard,minimax-text-01,32000,20,0.0625
realistic_Hard,minimax-text-01,32000,22,0.0547
realistic_Hard,minimax-text-01,32000,24,0.0547
realistic_Hard,minimax-text-01,32000,26,0.0312
realistic_Hard,minimax-text-01,32000,28,0.0469
realistic_Hard,minimax-text-01,32000,30,0.0312
realistic_Medium,gemini-1.5-flash-002,0,2,0.595
realistic_Medium,gemini-1.5-flash-002,0,3,0.695
realistic_Medium,gemini-1.5-flash-002,0,4,0.89
realistic_Medium,gemini-1.5-flash-002,0,5,0.895
realistic_Medium,gemini-1.5-flash-002,0,6,0.94
realistic_Medium,gemini-1.5-flash-002,0,7,0.885
realistic_Medium,gemini-1.5-flash-002,0,8,0.84
realistic_Medium,gemini-1.5-flash-002,0,9,0.81
realistic_Medium,gemini-1.5-flash-002,0,10,0.63
realistic_Medium,gemini-1.5-flash-002,0,11,0.72
realistic_Medium,gemini-1.5-flash-002,0,12,0.635
realistic_Medium,gemini-1.5-flash-002,0,13,0.55
realistic_Medium,gemini-1.5-flash-002,0,14,0.54
realistic_Medium,gemini-1.5-flash-002,0,15,0.595
realistic_Medium,gemini-1.5-flash-002,0,16,0.355
realistic_Medium,gemini-1.5-flash-002,0,17,0.43
realistic_Medium,gemini-1.5-flash-002,0,18,0.505
realistic_Medium,gemini-1.5-flash-002,0,19,0.38
realistic_Medium,gemini-1.5-flash-002,0,20,0.35
realistic_Medium,gemini-1.5-flash-002,0,21,0.345
realistic_Medium,gemini-1.5-flash-002,0,22,0.38
realistic_Medium,gemini-1.5-flash-002,0,23,0.375
realistic_Medium,gemini-1.5-flash-002,0,24,0.32
realistic_Medium,gemini-1.5-flash-002,0,25,0.295
realistic_Medium,gemini-1.5-flash-002,0,26,0.32
realistic_Medium,gemini-1.5-flash-002,0,27,0.255
realistic_Medium,gemini-1.5-flash-002,0,28,0.24
realistic_Medium,gemini-1.5-flash-002,0,29,0.22
realistic_Medium,gemini-1.5-flash-002,0,30,0.19
realistic_Medium,gemini-1.5-flash-002,8000,2,0.4844
realistic_Medium,gemini-1.5-flash-002,8000,4,0.7266
realistic_Medium,gemini-1.5-flash-002,8000,6,0.75
realistic_Medium,gemini-1.5-flash-002,8000,8,0.6016
realistic_Medium,gemini-1.5-flash-002,8000,10,0.3672
realistic_Medium,gemini-1.5-flash-002,8000,12,0.3125
realistic_Medium,gemini-1.5-flash-002,8000,14,0.2969
realistic_Medium,gemini-1.5-flash-002,8000,16,0.1406
realistic_Medium,gemini-1.5-flash-002,8000,18,0.1797
realistic_Medium,gemini-1.5-flash-002,8000,20,0.0859
realistic_Medium,gemini-1.5-flash-002,8000,22,0.1562
realistic_Medium,gemini-1.5-flash-002,8000,24,0.1406
realistic_Medium,gemini-1.5-flash-002,8000,26,0.0469
realistic_Medium,gemini-1.5-flash-002,8000,28,0.1406
realistic_Medium,gemini-1.5-flash-002,8000,30,0.0938
realistic_Medium,gemini-1.5-flash-002,16000,2,0.3937
realistic_Medium,gemini-1.5-flash-002,16000,4,0.6094
realistic_Medium,gemini-1.5-flash-002,16000,6,0.6328
realistic_Medium,gemini-1.5-flash-002,16000,8,0.4724
realistic_Medium,gemini-1.5-flash-002,16000,10,0.25
realistic_Medium,gemini-1.5-flash-002,16000,12,0.25
realistic_Medium,gemini-1.5-flash-002,16000,14,0.2656
realistic_Medium,gemini-1.5-flash-002,16000,16,0.1094
realistic_Medium,gemini-1.5-flash-002,16000,18,0.0968
realistic_Medium,gemini-1.5-flash-002,16000,20,0.0391
realistic_Medium,gemini-1.5-flash-002,16000,22,0.063
realistic_Medium,gemini-1.5-flash-002,16000,24,0.0703
realistic_Medium,gemini-1.5-flash-002,16000,26,0.0234
realistic_Medium,gemini-1.5-flash-002,16000,28,0.0078
realistic_Medium,gemini-1.5-flash-002,16000,30,0.0
realistic_Medium,gemini-1.5-flash-002,32000,2,0.4524
realistic_Medium,gemini-1.5-flash-002,32000,4,0.6172
realistic_Medium,gemini-1.5-flash-002,32000,6,0.4766
realistic_Medium,gemini-1.5-flash-002,32000,8,0.3984
realistic_Medium,gemini-1.5-flash-002,32000,10,0.25
realistic_Medium,gemini-1.5-flash-002,32000,12,0.1562
realistic_Medium,gemini-1.5-flash-002,32000,14,0.125
realistic_Medium,gemini-1.5-flash-002,32000,16,0.0781
realistic_Medium,gemini-1.5-flash-002,32000,18,0.0547
realistic_Medium,gemini-1.5-flash-002,32000,20,0.0391
realistic_Medium,gemini-1.5-flash-002,32000,22,0.0234
realistic_Medium,gemini-1.5-flash-002,32000,24,0.0312
realistic_Medium,gemini-1.5-flash-002,32000,26,0.0078
realistic_Medium,gemini-1.5-flash-002,32000,28,0.0156
realistic_Medium,gemini-1.5-flash-002,32000,30,0.0078
symbolic,minimax-text-01,0,1,0.98
symbolic,minimax-text-01,0,2,1.0
symbolic,minimax-text-01,0,3,0.97
symbolic,minimax-text-01,0,4,0.96
symbolic,minimax-text-01,0,5,0.9
symbolic,minimax-text-01,0,6,0.85
symbolic,minimax-text-01,0,7,0.78
symbolic,minimax-text-01,0,8,0.83
symbolic,minimax-text-01,0,9,0.79
symbolic,minimax-text-01,0,10,0.73
symbolic,minimax-text-01,0,11,0.67
symbolic,minimax-text-01,0,21,0.28
symbolic,minimax-text-01,0,31,0.12
symbolic,minimax-text-01,0,41,0.01
symbolic,minimax-text-01,0,51,0.01
symbolic,minimax-text-01,0,61,0.0
symbolic,minimax-text-01,0,71,0.0
symbolic,minimax-text-01,8000,1,0.94
symbolic,minimax-text-01,8000,2,0.53
symbolic,minimax-text-01,8000,3,0.2
symbolic,minimax-text-01,8000,4,0.14
symbolic,minimax-text-01,8000,5,0.06
symbolic,minimax-text-01,8000,6,0.09
symbolic,minimax-text-01,8000,7,0.03
symbolic,minimax-text-01,8000,8,0.05
symbolic,minimax-text-01,8000,9,0.06
symbolic,minimax-text-01,8000,10,0.01
symbolic,minimax-text-01,16000,1,0.91
symbolic,minimax-text-01,16000,2,0.44
symbolic,minimax-text-01,16000,3,0.19
symbolic,minimax-text-01,16000,4,0.16
symbolic,minimax-text-01,16000,5,0.1
symbolic,minimax-text-01,16000,6,0.06
symbolic,minimax-text-01,16000,7,0.03
symbolic,minimax-text-01,16000,8,0.04
symbolic,minimax-text-01,16000,9,0.01
symbolic,minimax-text-01,16000,10,0.01
symbolic,minimax-text-01,32000,1,0.9
symbolic,minimax-text-01,32000,2,0.3
symbolic,minimax-text-01,32000,3,0.1
symbolic,minimax-text-01,32000,4,0.06
symbolic,minimax-text-01,32000,5,0.08
symbolic,minimax-text-01,32000,6,0.05
symbolic,minimax-text-01,32000,7,0.01
symbolic,minimax-text-01,32000,8,0.02
symbolic,minimax-text-01,32000,9,0.0
symbolic,minimax-text-01,32000,10,0.01
symbolic,jamba-1.5-large,0,1,0.97
symbolic,jamba-1.5-large,0,3,0.87
symbolic,jamba-1.5-large,0,5,0.71
symbolic,jamba-1.5-large,0,7,0.56
symbolic,jamba-1.5-large,0,9,0.46
symbolic,jamba-1.5-large,0,11,0.35
symbolic,jamba-1.5-large,0,13,0.19
symbolic,jamba-1.5-large,0,15,0.18
symbolic,jamba-1.5-large,0,17,0.15
symbolic,jamba-1.5-large,0,19,0.08
symbolic,jamba-1.5-large,0,21,0.06
symbolic,jamba-1.5-large,0,23,0.08
symbolic,jamba-1.5-large,0,25,0.04
symbolic,jamba-1.5-large,0,27,0.05
symbolic,jamba-1.5-large,0,29,0.03
realistic_Medium,llama-3.1-8b-instruct,0,2,0.65
realistic_Medium,llama-3.1-8b-instruct,0,3,0.47
realistic_Medium,llama-3.1-8b-instruct,0,4,0.78
realistic_Medium,llama-3.1-8b-instruct,0,5,0.725
realistic_Medium,llama-3.1-8b-instruct,0,6,0.735
realistic_Medium,llama-3.1-8b-instruct,0,7,0.56
realistic_Medium,llama-3.1-8b-instruct,0,8,0.57
realistic_Medium,llama-3.1-8b-instruct,0,9,0.485
realistic_Medium,llama-3.1-8b-instruct,0,10,0.365
realistic_Medium,llama-3.1-8b-instruct,0,11,0.42
realistic_Medium,llama-3.1-8b-instruct,0,12,0.335
realistic_Medium,llama-3.1-8b-instruct,0,13,0.34
realistic_Medium,llama-3.1-8b-instruct,0,14,0.285
realistic_Medium,llama-3.1-8b-instruct,0,15,0.23
realistic_Medium,llama-3.1-8b-instruct,0,16,0.135
realistic_Medium,llama-3.1-8b-instruct,0,17,0.13
realistic_Medium,llama-3.1-8b-instruct,0,18,0.155
realistic_Medium,llama-3.1-8b-instruct,0,19,0.145
realistic_Medium,llama-3.1-8b-instruct,0,20,0.11
realistic_Medium,llama-3.1-8b-instruct,0,21,0.115
realistic_Medium,llama-3.1-8b-instruct,0,22,0.06
realistic_Medium,llama-3.1-8b-instruct,0,23,0.09
realistic_Medium,llama-3.1-8b-instruct,0,24,0.065
realistic_Medium,llama-3.1-8b-instruct,0,25,0.055
realistic_Medium,llama-3.1-8b-instruct,0,26,0.045
realistic_Medium,llama-3.1-8b-instruct,0,27,0.05
realistic_Medium,llama-3.1-8b-instruct,0,28,0.035
realistic_Medium,llama-3.1-8b-instruct,0,29,0.025
realistic_Medium,llama-3.1-8b-instruct,0,30,0.05
realistic_Medium,llama-3.1-8b-instruct,8000,2,0.24
realistic_Medium,llama-3.1-8b-instruct,8000,4,0.15
realistic_Medium,llama-3.1-8b-instruct,8000,6,0.235
realistic_Medium,llama-3.1-8b-instruct,8000,8,0.15
realistic_Medium,llama-3.1-8b-instruct,8000,10,0.04
realistic_Medium,llama-3.1-8b-instruct,8000,12,0.03
realistic_Medium,llama-3.1-8b-instruct,8000,14,0.05
realistic_Medium,llama-3.1-8b-instruct,8000,16,0.015
realistic_Medium,llama-3.1-8b-instruct,8000,18,0.03
realistic_Medium,llama-3.1-8b-instruct,8000,20,0.03
realistic_Medium,llama-3.1-8b-instruct,8000,22,0.005
realistic_Medium,llama-3.1-8b-instruct,8000,24,0.015
realistic_Medium,llama-3.1-8b-instruct,8000,26,0.03
realistic_Medium,llama-3.1-8b-instruct,8000,28,0.02
realistic_Medium,llama-3.1-8b-instruct,8000,30,0.01
realistic_Medium,llama-3.1-8b-instruct,16000,2,0.17
realistic_Medium,llama-3.1-8b-instruct,16000,4,0.175
realistic_Medium,llama-3.1-8b-instruct,16000,18,0.03
realistic_Medium,llama-3.1-8b-instruct,16000,20,0.01
realistic_Medium,llama-3.1-8b-instruct,16000,22,0.005
realistic_Medium,llama-3.1-8b-instruct,16000,24,0.02
realistic_Medium,llama-3.1-8b-instruct,16000,26,0.02
realistic_Medium,llama-3.1-8b-instruct,16000,28,0.01
realistic_Medium,llama-3.1-8b-instruct,16000,30,0.015
realistic_Medium,llama-3.1-8b-instruct,32000,2,0.135
realistic_Medium,llama-3.1-8b-instruct,32000,4,0.085
realistic_Medium,llama-3.1-8b-instruct,32000,6,0.14
realistic_Medium,llama-3.1-8b-instruct,32000,8,0.095
realistic_Medium,llama-3.1-8b-instruct,32000,10,0.055
realistic_Medium,llama-3.1-8b-instruct,32000,12,0.025
realistic_Medium,llama-3.1-8b-instruct,32000,14,0.02
realistic_Medium,llama-3.1-8b-instruct,32000,16,0.005
realistic_Medium,llama-3.1-8b-instruct,32000,18,0.015
realistic_Medium,llama-3.1-8b-instruct,32000,20,0.005
realistic_Medium,llama-3.1-8b-instruct,32000,22,0.025
realistic_Medium,llama-3.1-8b-instruct,32000,24,0.015
realistic_Medium,llama-3.1-8b-instruct,32000,26,0.01
realistic_Medium,llama-3.1-8b-instruct,32000,28,0.005
realistic_Medium,llama-3.1-8b-instruct,32000,30,0.03
realistic_Hard,claude-3.5-sonnet,0,2,0.9609
realistic_Hard,claude-3.5-sonnet,0,6,0.9375
realistic_Hard,claude-3.5-sonnet,0,10,0.9375
realistic_Hard,claude-3.5-sonnet,0,14,0.8047
realistic_Hard,claude-3.5-sonnet,0,18,0.6953
realistic_Hard,claude-3.5-sonnet,0,22,0.5156
realistic_Hard,claude-3.5-sonnet,0,26,0.2891
realistic_Hard,claude-3.5-sonnet,0,30,0.2656
realistic_Hard,claude-3.5-sonnet,0,35,0.134615
realistic_Hard,claude-3.5-sonnet,0,40,0.0673077
realistic_Hard,claude-3.5-sonnet,0,45,0.0384615
realistic_Hard,claude-3.5-sonnet,0,50,0.0480769
realistic_Medium,qwq-32b-preview,0,2,0.915
realistic_Medium,qwq-32b-preview,0,3,0.91
realistic_Medium,qwq-32b-preview,0,4,0.955
realistic_Medium,qwq-32b-preview,0,5,0.965
realistic_Medium,qwq-32b-preview,0,6,0.93
realistic_Medium,qwq-32b-preview,0,7,0.945
realistic_Medium,qwq-32b-preview,0,8,0.955
realistic_Medium,qwq-32b-preview,0,9,0.935
realistic_Medium,qwq-32b-preview,0,10,0.825
realistic_Medium,qwq-32b-preview,0,11,0.89
realistic_Medium,qwq-32b-preview,0,12,0.765
realistic_Medium,qwq-32b-preview,0,13,0.815
realistic_Medium,qwq-32b-preview,0,14,0.805
realistic_Medium,qwq-32b-preview,0,15,0.845
realistic_Medium,qwq-32b-preview,0,16,0.74
realistic_Medium,qwq-32b-preview,0,17,0.705
realistic_Medium,qwq-32b-preview,0,18,0.81
realistic_Medium,qwq-32b-preview,0,19,0.715
realistic_Medium,qwq-32b-preview,0,20,0.755
realistic_Medium,qwq-32b-preview,0,21,0.76
realistic_Medium,qwq-32b-preview,0,22,0.725
realistic_Medium,qwq-32b-preview,0,23,0.74
realistic_Medium,qwq-32b-preview,0,24,0.74
realistic_Medium,qwq-32b-preview,0,25,0.605
realistic_Medium,qwq-32b-preview,0,26,0.685
realistic_Medium,qwq-32b-preview,0,27,0.665
realistic_Medium,qwq-32b-preview,0,28,0.64
realistic_Medium,qwq-32b-preview,0,29,0.625
realistic_Medium,qwq-32b-preview,0,30,0.55
realistic_Medium,qwq-32b-preview,0,35,0.48125
realistic_Medium,qwq-32b-preview,0,40,0.35
realistic_Medium,qwq-32b-preview,0,45,0.23125
realistic_Medium,qwq-32b-preview,0,50,0.15
realistic_Medium,qwq-32b-preview,0,55,0.13125
realistic_Medium,qwq-32b-preview,0,60,0.1375
realistic_Medium,qwq-32b-preview,0,65,0.09375
realistic_Medium,qwq-32b-preview,0,70,0.01875
realistic_Medium,qwq-32b-preview,0,75,0.03125
realistic_Medium,qwq-32b-preview,0,80,0.0125
realistic_Medium,qwq-32b-preview,0,85,0.0625
realistic_Medium,qwq-32b-preview,0,90,0.0
symbolic,llama-3.1-8b-instruct,0,1,0.7
symbolic,llama-3.1-8b-instruct,0,2,0.71
symbolic,llama-3.1-8b-instruct,0,3,0.67
symbolic,llama-3.1-8b-instruct,0,4,0.55
symbolic,llama-3.1-8b-instruct,0,5,0.48
symbolic,llama-3.1-8b-instruct,0,6,0.39
symbolic,llama-3.1-8b-instruct,0,7,0.31
symbolic,llama-3.1-8b-instruct,0,8,0.23
symbolic,llama-3.1-8b-instruct,0,9,0.24
symbolic,llama-3.1-8b-instruct,0,10,0.11
symbolic,llama-3.1-8b-instruct,0,11,0.15
symbolic,llama-3.1-8b-instruct,0,12,0.1
symbolic,llama-3.1-8b-instruct,0,13,0.05
symbolic,llama-3.1-8b-instruct,0,14,0.01
symbolic,llama-3.1-8b-instruct,0,15,0.07
symbolic,llama-3.1-8b-instruct,0,16,0.06
symbolic,llama-3.1-8b-instruct,0,17,0.02
symbolic,llama-3.1-8b-instruct,0,18,0.03
symbolic,llama-3.1-8b-instruct,0,19,0.02
symbolic,llama-3.1-8b-instruct,0,20,0.01
symbolic,llama-3.1-8b-instruct,0,21,0.03
symbolic,llama-3.1-8b-instruct,0,22,0.02
symbolic,llama-3.1-8b-instruct,0,23,0.0
symbolic,llama-3.1-8b-instruct,0,24,0.0
symbolic,llama-3.1-8b-instruct,0,25,0.0
symbolic,llama-3.1-8b-instruct,0,26,0.0
symbolic,llama-3.1-8b-instruct,0,27,0.0
symbolic,llama-3.1-8b-instruct,0,28,0.01
symbolic,llama-3.1-8b-instruct,0,29,0.0
symbolic,llama-3.1-8b-instruct,8000,1,0.6
symbolic,llama-3.1-8b-instruct,8000,2,0.19
symbolic,llama-3.1-8b-instruct,8000,3,0.07
symbolic,llama-3.1-8b-instruct,8000,4,0.03
symbolic,llama-3.1-8b-instruct,16000,1,0.46
symbolic,llama-3.1-8b-instruct,16000,2,0.07
symbolic,llama-3.1-8b-instruct,16000,3,0.11
symbolic,llama-3.1-8b-instruct,16000,4,0.04
symbolic,llama-3.1-8b-instruct,16000,5,0.02
symbolic,llama-3.1-8b-instruct,32000,1,0.36
symbolic,llama-3.1-8b-instruct,32000,2,0.1
symbolic,llama-3.1-8b-instruct,32000,3,0.16
symbolic,llama-3.1-8b-instruct,32000,4,0.04
symbolic,llama-3.1-8b-instruct,32000,5,0.04
symbolic,llama-3.1-8b-instruct,32000,6,0.04
symbolic,qwq-32b-preview,0,1,0.89
symbolic,qwq-32b-preview,0,6,0.95
symbolic,qwq-32b-preview,0,11,0.96
symbolic,qwq-32b-preview,0,16,0.86
symbolic,qwq-32b-preview,0,21,0.8
symbolic,qwq-32b-preview,0,26,0.64
symbolic,qwq-32b-preview,0,31,0.42
symbolic,qwq-32b-preview,0,36,0.31
symbolic,qwq-32b-preview,0,41,0.27
symbolic,qwq-32b-preview,0,46,0.35
symbolic,qwq-32b-preview,0,51,0.15
symbolic,qwq-32b-preview,0,56,0.15
symbolic,qwq-32b-preview,0,61,0.08
symbolic,qwq-32b-preview,0,66,0.08
symbolic,qwq-32b-preview,0,71,0.11
symbolic,qwq-32b-preview,0,76,0.1
symbolic,qwq-32b-preview,0,81,0.09
symbolic,qwq-32b-preview,0,86,0.05
symbolic,qwq-32b-preview,0,91,0.01
symbolic,qwq-32b-preview,0,96,0.1
symbolic,qwq-32b-preview,0,101,0.04
symbolic,qwq-32b-preview,0,106,0.03
symbolic,qwq-32b-preview,0,111,0.05
symbolic,qwq-32b-preview,0,116,0.03
symbolic,qwq-32b-preview,8000,1,0.72
symbolic,qwq-32b-preview,8000,2,0.49
symbolic,qwq-32b-preview,8000,3,0.29
symbolic,qwq-32b-preview,8000,4,0.15
symbolic,qwq-32b-preview,8000,5,0.11
symbolic,qwq-32b-preview,8000,6,0.09
symbolic,qwq-32b-preview,8000,7,0.04
symbolic,qwq-32b-preview,8000,8,0.03
symbolic,qwq-32b-preview,8000,9,0.01
symbolic,qwq-32b-preview,16000,1,0.51
symbolic,qwq-32b-preview,16000,2,0.17
symbolic,qwq-32b-preview,16000,3,0.15
symbolic,qwq-32b-preview,16000,4,0.04
symbolic,qwq-32b-preview,16000,5,0.04
symbolic,qwq-32b-preview,16000,6,0.01
symbolic,qwq-32b-preview,16000,7,0.04
symbolic,qwq-32b-preview,16000,8,0.0
symbolic,qwq-32b-preview,16000,9,0.0
symbolic,qwen-2.5-72b-instruct,0,1,1.0
symbolic,qwen-2.5-72b-instruct,0,3,1.0
symbolic,qwen-2.5-72b-instruct,0,5,0.93
symbolic,qwen-2.5-72b-instruct,0,7,0.9
symbolic,qwen-2.5-72b-instruct,0,9,0.82
symbolic,qwen-2.5-72b-instruct,0,11,0.72
symbolic,qwen-2.5-72b-instruct,0,13,0.65
symbolic,qwen-2.5-72b-instruct,0,15,0.63
symbolic,qwen-2.5-72b-instruct,0,17,0.6
symbolic,qwen-2.5-72b-instruct,0,19,0.49
symbolic,qwen-2.5-72b-instruct,0,21,0.42
symbolic,qwen-2.5-72b-instruct,0,23,0.33
symbolic,qwen-2.5-72b-instruct,0,25,0.3
symbolic,qwen-2.5-72b-instruct,0,27,0.25
symbolic,qwen-2.5-72b-instruct,0,29,0.27
symbolic,qwen-2.5-72b-instruct,0,31,0.18
symbolic,qwen-2.5-72b-instruct,0,33,0.23
symbolic,qwen-2.5-72b-instruct,0,35,0.14
symbolic,qwen-2.5-72b-instruct,0,37,0.15
symbolic,qwen-2.5-72b-instruct,0,39,0.1
symbolic,qwen-2.5-72b-instruct,0,41,0.13
symbolic,qwen-2.5-72b-instruct,0,43,0.07
symbolic,qwen-2.5-72b-instruct,0,45,0.06
symbolic,qwen-2.5-72b-instruct,0,47,0.09
symbolic,qwen-2.5-72b-instruct,0,49,0.05
symbolic,qwen-2.5-72b-instruct,0,51,0.06
symbolic,qwen-2.5-72b-instruct,0,53,0.09
symbolic,qwen-2.5-72b-instruct,0,55,0.01
symbolic,qwen-2.5-72b-instruct,0,57,0.06
symbolic,qwen-2.5-72b-instruct,0,59,0.02
symbolic,qwen-2.5-72b-instruct,8000,1,0.77
symbolic,qwen-2.5-72b-instruct,8000,2,0.46
symbolic,qwen-2.5-72b-instruct,8000,3,0.17
symbolic,qwen-2.5-72b-instruct,8000,4,0.08
symbolic,qwen-2.5-72b-instruct,8000,5,0.07
symbolic,qwen-2.5-72b-instruct,8000,6,0.01
symbolic,qwen-2.5-72b-instruct,8000,7,0.01
symbolic,qwen-2.5-72b-instruct,8000,8,0.01
symbolic,qwen-2.5-72b-instruct,8000,9,0.0
symbolic,qwen-2.5-72b-instruct,16000,1,0.71
symbolic,qwen-2.5-72b-instruct,16000,2,0.25
symbolic,qwen-2.5-72b-instruct,16000,3,0.12
symbolic,qwen-2.5-72b-instruct,16000,4,0.1
symbolic,qwen-2.5-72b-instruct,16000,5,0.06
symbolic,qwen-2.5-72b-instruct,16000,6,0.01
symbolic,qwen-2.5-72b-instruct,16000,7,0.02
symbolic,qwen-2.5-72b-instruct,16000,8,0.0
symbolic,qwen-2.5-72b-instruct,16000,9,0.0
symbolic,qwen-2.5-72b-instruct,32000,1,0.34
symbolic,qwen-2.5-72b-instruct,32000,2,0.06
symbolic,qwen-2.5-72b-instruct,32000,3,0.04
symbolic,qwen-2.5-72b-instruct,32000,4,0.04
realistic_Hard,deepseek-v3,0,2,0.88
realistic_Hard,deepseek-v3,0,3,0.915
realistic_Hard,deepseek-v3,0,4,0.905
realistic_Hard,deepseek-v3,0,5,0.9
realistic_Hard,deepseek-v3,0,6,0.905
realistic_Hard,deepseek-v3,0,7,0.815
realistic_Hard,deepseek-v3,0,8,0.865
realistic_Hard,deepseek-v3,0,9,0.885
realistic_Hard,deepseek-v3,0,10,0.785
realistic_Hard,deepseek-v3,0,11,0.7487
realistic_Hard,deepseek-v3,0,12,0.7538
realistic_Hard,deepseek-v3,0,13,0.69
realistic_Hard,deepseek-v3,0,14,0.755
realistic_Hard,deepseek-v3,0,15,0.725
realistic_Hard,deepseek-v3,0,16,0.725
realistic_Hard,deepseek-v3,0,17,0.695
realistic_Hard,deepseek-v3,0,18,0.69
realistic_Hard,deepseek-v3,0,19,0.63
realistic_Hard,deepseek-v3,0,20,0.6
realistic_Hard,deepseek-v3,0,21,0.54
realistic_Hard,deepseek-v3,0,22,0.485
realistic_Hard,deepseek-v3,0,23,0.53
realistic_Hard,deepseek-v3,0,24,0.4673
realistic_Hard,deepseek-v3,0,25,0.47
realistic_Hard,deepseek-v3,0,26,0.4
realistic_Hard,deepseek-v3,0,27,0.4
realistic_Hard,deepseek-v3,0,28,0.395
realistic_Hard,deepseek-v3,0,29,0.43
realistic_Hard,deepseek-v3,0,30,0.355
realistic_Hard,deepseek-v3,0,35,0.30625
realistic_Hard,deepseek-v3,0,40,0.1625
realistic_Hard,deepseek-v3,0,45,0.1875
realistic_Hard,deepseek-v3,0,50,0.1375
realistic_Hard,deepseek-v3,0,55,0.08125
realistic_Hard,deepseek-v3,0,60,0.0375
realistic_Hard,deepseek-v3,8000,2,0.8719
realistic_Hard,deepseek-v3,8000,4,0.84
realistic_Hard,deepseek-v3,8000,6,0.72
realistic_Hard,deepseek-v3,8000,8,0.56
realistic_Hard,deepseek-v3,8000,10,0.5
realistic_Hard,deepseek-v3,8000,12,0.48
realistic_Hard,deepseek-v3,8000,14,0.425
realistic_Hard,deepseek-v3,8000,16,0.39
realistic_Hard,deepseek-v3,8000,18,0.31
realistic_Hard,deepseek-v3,8000,20,0.3668
realistic_Hard,deepseek-v3,8000,22,0.305
realistic_Hard,deepseek-v3,8000,24,0.325
realistic_Hard,deepseek-v3,8000,26,0.365
realistic_Hard,deepseek-v3,8000,28,0.34
realistic_Hard,deepseek-v3,8000,30,0.395
realistic_Hard,deepseek-v3,16000,2,0.745
realistic_Hard,deepseek-v3,16000,4,0.72
realistic_Hard,deepseek-v3,16000,6,0.495
realistic_Hard,deepseek-v3,16000,8,0.4
realistic_Hard,deepseek-v3,16000,10,0.23
realistic_Hard,deepseek-v3,16000,12,0.17
realistic_Hard,deepseek-v3,16000,14,0.11
realistic_Hard,deepseek-v3,16000,16,0.075
realistic_Hard,deepseek-v3,16000,18,0.07
realistic_Hard,deepseek-v3,16000,20,0.055
realistic_Hard,deepseek-v3,16000,22,0.035
realistic_Hard,deepseek-v3,16000,24,0.0503
realistic_Hard,deepseek-v3,16000,26,0.025
realistic_Hard,deepseek-v3,16000,28,0.02
realistic_Hard,deepseek-v3,16000,30,0.055
realistic_Hard,deepseek-v3,32000,2,0.6475
realistic_Hard,deepseek-v3,32000,4,0.565
realistic_Hard,deepseek-v3,32000,6,0.3869
realistic_Hard,deepseek-v3,32000,8,0.19
realistic_Hard,deepseek-v3,32000,10,0.0761421
realistic_Hard,deepseek-v3,32000,12,0.0654762
realistic_Hard,deepseek-v3,32000,14,0.0494505
symbolic,gpt-4o-2024-11-20,0,1,0.97
symbolic,gpt-4o-2024-11-20,0,4,0.99
symbolic,gpt-4o-2024-11-20,0,7,0.96
symbolic,gpt-4o-2024-11-20,0,10,0.97
symbolic,gpt-4o-2024-11-20,0,13,0.76
symbolic,gpt-4o-2024-11-20,0,16,0.56
symbolic,gpt-4o-2024-11-20,0,19,0.63
symbolic,gpt-4o-2024-11-20,0,22,0.54
symbolic,gpt-4o-2024-11-20,0,25,0.45
symbolic,gpt-4o-2024-11-20,0,28,0.39
symbolic,gpt-4o-2024-11-20,0,31,0.26
symbolic,gpt-4o-2024-11-20,0,34,0.2
symbolic,gpt-4o-2024-11-20,0,37,0.22
symbolic,gpt-4o-2024-11-20,0,40,0.11
symbolic,gpt-4o-2024-11-20,0,43,0.11
symbolic,gpt-4o-2024-11-20,0,46,0.06
symbolic,gpt-4o-2024-11-20,0,49,0.06
symbolic,gpt-4o-2024-11-20,0,52,0.05
symbolic,gpt-4o-2024-11-20,0,55,0.04
symbolic,gpt-4o-2024-11-20,0,58,0.02
symbolic,gpt-4o-2024-11-20,0,61,0.01
symbolic,gpt-4o-2024-11-20,0,64,0.02
symbolic,gpt-4o-2024-11-20,0,67,0.0
symbolic,gpt-4o-2024-11-20,0,70,0.02
symbolic,gpt-4o-2024-11-20,0,73,0.01
symbolic,gpt-4o-2024-11-20,0,76,0.0
symbolic,gpt-4o-2024-11-20,0,79,0.0
symbolic,gpt-4o-2024-11-20,0,82,0.0
symbolic,gpt-4o-2024-11-20,0,85,0.0
symbolic,gpt-4o-2024-11-20,0,88,0.01
realistic_Hard,gpt-4o-2024-11-20,0,2,0.8516
realistic_Hard,gpt-4o-2024-11-20,0,6,0.8984
realistic_Hard,gpt-4o-2024-11-20,0,10,0.6172
realistic_Hard,gpt-4o-2024-11-20,0,14,0.6172
realistic_Hard,gpt-4o-2024-11-20,0,14,0.5859
realistic_Hard,gpt-4o-2024-11-20,0,18,0.5859
realistic_Hard,gpt-4o-2024-11-20,0,18,0.4609
realistic_Hard,gpt-4o-2024-11-20,0,22,0.4609
realistic_Hard,gpt-4o-2024-11-20,0,22,0.2422
realistic_Hard,gpt-4o-2024-11-20,0,26,0.1719
realistic_Hard,gpt-4o-2024-11-20,0,30,0.0781
symbolic,mistral-large-2411,0,1,0.98
symbolic,mistral-large-2411,0,4,0.94
symbolic,mistral-large-2411,0,7,0.89
symbolic,mistral-large-2411,0,10,0.96
symbolic,mistral-large-2411,0,13,0.91
symbolic,mistral-large-2411,0,16,0.73
symbolic,mistral-large-2411,0,19,0.77
symbolic,mistral-large-2411,0,22,0.53
symbolic,mistral-large-2411,0,25,0.44
symbolic,mistral-large-2411,0,28,0.29
symbolic,mistral-large-2411,0,31,0.23
symbolic,mistral-large-2411,0,34,0.17
symbolic,mistral-large-2411,0,37,0.09
symbolic,mistral-large-2411,0,40,0.1
symbolic,mistral-large-2411,0,43,0.06
symbolic,mistral-large-2411,0,46,0.07
symbolic,mistral-large-2411,0,49,0.02
symbolic,mistral-large-2411,0,52,0.04
symbolic,mistral-large-2411,0,55,0.03
symbolic,mistral-large-2411,0,58,0.03
symbolic,mistral-large-2411,8000,1,0.57
symbolic,mistral-large-2411,8000,2,0.26
symbolic,mistral-large-2411,8000,3,0.12
symbolic,mistral-large-2411,8000,4,0.04
symbolic,mistral-large-2411,8000,5,0.02
symbolic,mistral-large-2411,8000,6,0.0
symbolic,mistral-large-2411,8000,7,0.01
symbolic,mistral-large-2411,8000,8,0.01
symbolic,mistral-large-2411,8000,9,0.0
symbolic,mistral-large-2411,16000,1,0.2
symbolic,mistral-large-2411,16000,2,0.08
symbolic,mistral-large-2411,16000,3,0.06
symbolic,mistral-large-2411,16000,4,0.01
symbolic,mistral-large-2411,16000,5,0.01
symbolic,mistral-large-2411,32000,1,0.01
symbolic,mistral-large-2411,32000,2,0.0
symbolic,mistral-large-2411,32000,3,0.01
symbolic,mistral-large-2411,32000,4,0.0
realistic_Hard,gpt-4o-mini,0,2,0.6025
realistic_Hard,gpt-4o-mini,0,4,0.7944
realistic_Hard,gpt-4o-mini,0,6,0.7944
realistic_Hard,gpt-4o-mini,0,8,0.6653
realistic_Hard,gpt-4o-mini,0,10,0.504
realistic_Hard,gpt-4o-mini,0,12,0.4274
realistic_Hard,gpt-4o-mini,0,14,0.3105
realistic_Hard,gpt-4o-mini,0,14,0.3105
realistic_Hard,gpt-4o-mini,0,16,0.1976
realistic_Hard,gpt-4o-mini,0,18,0.1976
realistic_Hard,gpt-4o-mini,0,20,0.1008
realistic_Hard,gpt-4o-mini,0,22,0.0968
realistic_Hard,gpt-4o-mini,0,24,0.0484
realistic_Hard,gpt-4o-mini,0,26,0.0403
realistic_Hard,gpt-4o-mini,0,26,0.0524
realistic_Hard,gpt-4o-mini,0,28,0.0524
realistic_Hard,gpt-4o-mini,0,30,0.0645
realistic_Hard,gpt-4o-mini,8000,2,0.5938
realistic_Hard,gpt-4o-mini,8000,4,0.6484
realistic_Hard,gpt-4o-mini,8000,6,0.4844
realistic_Hard,gpt-4o-mini,8000,8,0.2812
realistic_Hard,gpt-4o-mini,8000,10,0.1719
realistic_Hard,gpt-4o-mini,8000,12,0.1562
realistic_Hard,gpt-4o-mini,8000,14,0.1016
realistic_Hard,gpt-4o-mini,8000,16,0.0625
realistic_Hard,gpt-4o-mini,8000,18,0.0781
realistic_Hard,gpt-4o-mini,8000,20,0.1016
realistic_Hard,gpt-4o-mini,16000,2,0.5391
realistic_Hard,gpt-4o-mini,16000,4,0.5781
realistic_Hard,gpt-4o-mini,16000,6,0.3984
realistic_Hard,gpt-4o-mini,16000,8,0.1797
realistic_Hard,gpt-4o-mini,16000,10,0.1016
realistic_Hard,gpt-4o-mini,16000,12,0.0625
realistic_Hard,gpt-4o-mini,16000,14,0.0625
realistic_Hard,gpt-4o-mini,16000,16,0.0391
realistic_Hard,gpt-4o-mini,16000,18,0.0781
realistic_Hard,gpt-4o-mini,16000,20,0.0938
realistic_Hard,gpt-4o-mini,32000,2,0.4766
realistic_Hard,gpt-4o-mini,32000,4,0.4531
realistic_Hard,gpt-4o-mini,32000,6,0.3281
realistic_Hard,gpt-4o-mini,32000,8,0.1562
realistic_Hard,gpt-4o-mini,32000,10,0.0703
realistic_Hard,gpt-4o-mini,32000,12,0.0859
realistic_Hard,gpt-4o-mini,32000,14,0.1094
realistic_Hard,gpt-4o-mini,32000,16,0.0391
realistic_Hard,gpt-4o-mini,32000,18,0.0547
realistic_Hard,gpt-4o-mini,32000,20,0.0469
realistic_Medium,deepseek-r1,0,10,0.7891
realistic_Medium,deepseek-r1,0,20,0.875
realistic_Medium,deepseek-r1,0,30,0.9531
realistic_Medium,deepseek-r1,0,40,0.8942
realistic_Medium,deepseek-r1,0,50,0.9135
realistic_Medium,deepseek-r1,0,60,0.9038
realistic_Medium,deepseek-r1,0,70,0.8462
realistic_Medium,deepseek-r1,0,80,0.8077
realistic_Medium,deepseek-r1,0,90,0.7308
realistic_Medium,deepseek-r1,0,100,0.5769
realistic_Medium,deepseek-r1,0,110,0.5769
realistic_Medium,deepseek-r1,0,120,0.5096
realistic_Medium,deepseek-r1,0,130,0.3654
realistic_Medium,deepseek-r1,0,140,0.2703
realistic_Medium,deepseek-r1,0,150,0.2658
realistic_Medium,claude-3.5-sonnet,0,2,0.9531
realistic_Medium,claude-3.5-sonnet,0,6,0.9844
realistic_Medium,claude-3.5-sonnet,0,10,0.8281
realistic_Medium,claude-3.5-sonnet,0,14,0.8281
realistic_Medium,claude-3.5-sonnet,0,18,0.8672
realistic_Medium,claude-3.5-sonnet,0,22,0.8359
realistic_Medium,claude-3.5-sonnet,0,26,0.6953
realistic_Medium,claude-3.5-sonnet,0,30,0.5547
realistic_Medium,claude-3.5-sonnet,0,35,0.5
realistic_Medium,claude-3.5-sonnet,0,40,0.384615
realistic_Medium,claude-3.5-sonnet,0,45,0.326923
realistic_Medium,claude-3.5-sonnet,0,50,0.0125
realistic_Medium,claude-3.5-sonnet,0,55,0.240385
realistic_Medium,claude-3.5-sonnet,0,60,0.0673077
realistic_Medium,claude-3.5-sonnet,0,65,0.0961538
realistic_Medium,claude-3.5-sonnet,0,70,0.0480769
realistic_Medium,qwen-2.5-7b-instruct,0,2,0.685
realistic_Medium,qwen-2.5-7b-instruct,0,3,0.67
realistic_Medium,qwen-2.5-7b-instruct,0,4,0.82
realistic_Medium,qwen-2.5-7b-instruct,0,5,0.82
realistic_Medium,qwen-2.5-7b-instruct,0,6,0.775
realistic_Medium,qwen-2.5-7b-instruct,0,7,0.705
realistic_Medium,qwen-2.5-7b-instruct,0,8,0.655
realistic_Medium,qwen-2.5-7b-instruct,0,9,0.605
realistic_Medium,qwen-2.5-7b-instruct,0,10,0.465
realistic_Medium,qwen-2.5-7b-instruct,0,11,0.43
realistic_Medium,qwen-2.5-7b-instruct,0,12,0.355
realistic_Medium,qwen-2.5-7b-instruct,0,13,0.35
realistic_Medium,qwen-2.5-7b-instruct,0,14,0.295
realistic_Medium,qwen-2.5-7b-instruct,0,15,0.235
realistic_Medium,qwen-2.5-7b-instruct,0,16,0.18
realistic_Medium,qwen-2.5-7b-instruct,0,17,0.17
realistic_Medium,qwen-2.5-7b-instruct,0,18,0.15
realistic_Medium,qwen-2.5-7b-instruct,0,19,0.155
realistic_Medium,qwen-2.5-7b-instruct,0,20,0.155
realistic_Medium,qwen-2.5-7b-instruct,0,21,0.075
realistic_Medium,qwen-2.5-7b-instruct,0,22,0.055
realistic_Medium,qwen-2.5-7b-instruct,0,23,0.085
realistic_Medium,qwen-2.5-7b-instruct,0,24,0.075
realistic_Medium,qwen-2.5-7b-instruct,0,25,0.06
realistic_Medium,qwen-2.5-7b-instruct,0,26,0.015
realistic_Medium,qwen-2.5-7b-instruct,0,27,0.035
realistic_Medium,qwen-2.5-7b-instruct,0,28,0.065
realistic_Medium,qwen-2.5-7b-instruct,0,29,0.055
realistic_Medium,qwen-2.5-7b-instruct,0,30,0.03
realistic_Medium,qwen-2.5-7b-instruct,8000,2,0.32
realistic_Medium,qwen-2.5-7b-instruct,8000,4,0.435
realistic_Medium,qwen-2.5-7b-instruct,8000,6,0.295
realistic_Medium,qwen-2.5-7b-instruct,8000,8,0.23
realistic_Medium,qwen-2.5-7b-instruct,8000,10,0.16
realistic_Medium,qwen-2.5-7b-instruct,8000,12,0.085
realistic_Medium,qwen-2.5-7b-instruct,8000,14,0.085
realistic_Medium,qwen-2.5-7b-instruct,8000,16,0.055
realistic_Medium,qwen-2.5-7b-instruct,8000,18,0.03
realistic_Medium,qwen-2.5-7b-instruct,8000,20,0.03
realistic_Medium,qwen-2.5-7b-instruct,8000,22,0.045
realistic_Medium,qwen-2.5-7b-instruct,8000,24,0.03
realistic_Medium,qwen-2.5-7b-instruct,8000,26,0.04
realistic_Medium,qwen-2.5-7b-instruct,8000,28,0.04
realistic_Medium,qwen-2.5-7b-instruct,8000,30,0.035
realistic_Medium,qwen-2.5-7b-instruct,16000,2,0.295
realistic_Medium,qwen-2.5-7b-instruct,16000,4,0.36
realistic_Medium,qwen-2.5-7b-instruct,16000,6,0.355
realistic_Medium,qwen-2.5-7b-instruct,16000,8,0.16
realistic_Medium,qwen-2.5-7b-instruct,16000,10,0.085
realistic_Medium,qwen-2.5-7b-instruct,16000,12,0.095
realistic_Medium,qwen-2.5-7b-instruct,16000,14,0.03
realistic_Medium,qwen-2.5-7b-instruct,16000,16,0.035
realistic_Medium,qwen-2.5-7b-instruct,16000,18,0.04
realistic_Medium,qwen-2.5-7b-instruct,16000,20,0.045
realistic_Medium,qwen-2.5-7b-instruct,16000,22,0.03
realistic_Medium,qwen-2.5-7b-instruct,16000,24,0.055
realistic_Medium,qwen-2.5-7b-instruct,16000,26,0.05
realistic_Medium,qwen-2.5-7b-instruct,16000,28,0.07
realistic_Medium,qwen-2.5-7b-instruct,16000,30,0.025
realistic_Medium,qwen-2.5-7b-instruct,32000,2,0.235
realistic_Medium,qwen-2.5-7b-instruct,32000,4,0.42
realistic_Medium,qwen-2.5-7b-instruct,32000,6,0.335
realistic_Medium,qwen-2.5-7b-instruct,32000,8,0.165
realistic_Medium,qwen-2.5-7b-instruct,32000,10,0.085
realistic_Medium,qwen-2.5-7b-instruct,32000,12,0.06
realistic_Medium,qwen-2.5-7b-instruct,32000,14,0.06
realistic_Medium,qwen-2.5-7b-instruct,32000,16,0.025
realistic_Medium,qwen-2.5-7b-instruct,32000,18,0.05
realistic_Medium,qwen-2.5-7b-instruct,32000,20,0.035
realistic_Medium,qwen-2.5-7b-instruct,32000,22,0.03
realistic_Medium,qwen-2.5-7b-instruct,32000,24,0.025
realistic_Medium,qwen-2.5-7b-instruct,32000,26,0.055
realistic_Medium,qwen-2.5-7b-instruct,32000,28,0.025
realistic_Medium,qwen-2.5-7b-instruct,32000,30,0.045
realistic_Hard,o1-mini,0,10,0.9615385
realistic_Hard,o1-mini,0,20,0.8653845
realistic_Hard,o1-mini,0,30,0.692308
realistic_Hard,o1-mini,0,40,0.548077
realistic_Hard,o1-mini,0,50,0.49035
realistic_Hard,o1-mini,0,60,0.278847
realistic_Hard,o1-mini,0,70,0.15098035
realistic_Hard,o1-mini,0,80,0.182692
realistic_Hard,o1-mini,0,90,0.098039
realistic_Medium,gemini-1.5-pro-002,0,2,0.8359
realistic_Medium,gemini-1.5-pro-002,0,6,0.9766
realistic_Medium,gemini-1.5-pro-002,0,10,0.7656
realistic_Medium,gemini-1.5-pro-002,0,14,0.75
realistic_Medium,gemini-1.5-pro-002,0,18,0.6875
realistic_Medium,gemini-1.5-pro-002,0,22,0.6406
realistic_Medium,gemini-1.5-pro-002,0,26,0.6172
realistic_Medium,gemini-1.5-pro-002,0,30,0.5312
realistic_Medium,gemini-1.5-pro-002,0,35,0.528846
realistic_Medium,gemini-1.5-pro-002,0,40,0.375
realistic_Medium,gemini-1.5-pro-002,0,45,0.307692
realistic_Medium,gemini-1.5-pro-002,0,50,0.423077
realistic_Medium,gemini-1.5-pro-002,0,55,0.317318
realistic_Medium,gemini-1.5-pro-002,0,60,0.221154
realistic_Medium,gemini-1.5-pro-002,0,65,0.240385
realistic_Medium,gemini-1.5-pro-002,0,70,0.125
realistic_Medium,gemini-1.5-pro-002,0,75,0.0865385
realistic_Medium,gemini-1.5-pro-002,0,80,0.115385
realistic_Medium,gemini-1.5-pro-002,0,85,0.125
realistic_Medium,gemini-1.5-pro-002,0,90,0.0576923
realistic_Medium,gemini-1.5-pro-002,0,95,0.0192308
realistic_Medium,gemini-1.5-pro-002,0,100,0.0288462
realistic_Medium,gemini-1.5-pro-002,8000,2,0.8516
realistic_Medium,gemini-1.5-pro-002,8000,6,0.8828
realistic_Medium,gemini-1.5-pro-002,8000,10,0.5312
realistic_Medium,gemini-1.5-pro-002,8000,14,0.4922
realistic_Medium,gemini-1.5-pro-002,8000,18,0.3828
realistic_Medium,gemini-1.5-pro-002,8000,22,0.2969
realistic_Medium,gemini-1.5-pro-002,8000,26,0.2969
realistic_Medium,gemini-1.5-pro-002,8000,30,0.2656
realistic_Medium,gemini-1.5-pro-002,16000,2,0.7969
realistic_Medium,gemini-1.5-pro-002,16000,6,0.8828
realistic_Medium,gemini-1.5-pro-002,16000,2,0.7422
realistic_Medium,gemini-1.5-pro-002,16000,6,0.8281
realistic_Medium,gemini-1.5-pro-002,16000,10,0.6172
realistic_Medium,gemini-1.5-pro-002,16000,14,0.4297
realistic_Medium,gemini-1.5-pro-002,16000,18,0.3281
realistic_Medium,gemini-1.5-pro-002,16000,22,0.1811
realistic_Medium,gemini-1.5-pro-002,16000,26,0.0781
realistic_Medium,gemini-1.5-pro-002,16000,30,0.1016
realistic_Medium,gemini-1.5-pro-002,32000,2,0.7734
realistic_Medium,gemini-1.5-pro-002,32000,6,0.7734
realistic_Medium,gemini-1.5-pro-002,32000,10,0.5547
realistic_Medium,gemini-1.5-pro-002,32000,14,0.3594
realistic_Medium,gemini-1.5-pro-002,32000,18,0.2656
realistic_Medium,gemini-1.5-pro-002,32000,22,0.2109
realistic_Medium,gemini-1.5-pro-002,32000,26,0.0703
realistic_Medium,gemini-1.5-pro-002,32000,30,0.0859
realistic_Medium,o1-mini,0,10,0.8653845
realistic_Medium,o1-mini,0,20,0.86
realistic_Medium,o1-mini,0,30,0.8942305
realistic_Medium,o1-mini,0,40,0.8653845
realistic_Medium,o1-mini,0,50,0.846154
realistic_Medium,o1-mini,0,60,0.701923
realistic_Medium,o1-mini,0,70,0.435294
realistic_Medium,o1-mini,0,80,0.4423075
realistic_Medium,o1-mini,0,90,0.221154
realistic_Medium,o1-mini,0,100,0.182692
realistic_Medium,o1-mini,0,110,0.12500005
realistic_Medium,o1-mini,0,120,0.09615405
realistic_Medium,llama-3.1-405b-instruct,0,2,0.7958
realistic_Medium,llama-3.1-405b-instruct,0,3,0.78
realistic_Medium,llama-3.1-405b-instruct,0,4,0.96
realistic_Medium,llama-3.1-405b-instruct,0,5,0.91
realistic_Medium,llama-3.1-405b-instruct,0,6,0.935
realistic_Medium,llama-3.1-405b-instruct,0,7,0.905
realistic_Medium,llama-3.1-405b-instruct,0,8,0.83
realistic_Medium,llama-3.1-405b-instruct,0,9,0.855
realistic_Medium,llama-3.1-405b-instruct,0,10,0.71
realistic_Medium,llama-3.1-405b-instruct,0,11,0.755
realistic_Medium,llama-3.1-405b-instruct,0,12,0.65
realistic_Medium,llama-3.1-405b-instruct,0,13,0.565
realistic_Medium,llama-3.1-405b-instruct,0,14,0.59
realistic_Medium,llama-3.1-405b-instruct,0,15,0.565
realistic_Medium,llama-3.1-405b-instruct,0,16,0.415
realistic_Medium,llama-3.1-405b-instruct,0,17,0.45
realistic_Medium,llama-3.1-405b-instruct,0,18,0.375
realistic_Medium,llama-3.1-405b-instruct,0,19,0.365
realistic_Medium,llama-3.1-405b-instruct,0,20,0.33
realistic_Medium,llama-3.1-405b-instruct,0,21,0.25
realistic_Medium,llama-3.1-405b-instruct,0,22,0.2
realistic_Medium,llama-3.1-405b-instruct,0,23,0.125
realistic_Medium,llama-3.1-405b-instruct,0,24,0.125
realistic_Medium,llama-3.1-405b-instruct,0,25,0.08
realistic_Medium,llama-3.1-405b-instruct,0,26,0.05
realistic_Medium,llama-3.1-405b-instruct,0,27,0.03
realistic_Medium,llama-3.1-405b-instruct,0,28,0.01
realistic_Medium,llama-3.1-405b-instruct,0,29,0.0
realistic_Medium,llama-3.1-405b-instruct,0,30,0.005
realistic_Hard,jamba-1.5-large,0,2,0.7266
realistic_Hard,jamba-1.5-large,0,4,0.5078
realistic_Hard,jamba-1.5-large,0,6,0.2812
realistic_Hard,jamba-1.5-large,0,8,0.1094
realistic_Hard,jamba-1.5-large,0,10,0.1484
realistic_Hard,jamba-1.5-large,0,12,0.1641
realistic_Hard,jamba-1.5-large,0,14,0.0781
realistic_Hard,jamba-1.5-large,0,16,0.0703
realistic_Hard,jamba-1.5-large,0,18,0.0625
realistic_Hard,jamba-1.5-large,0,20,0.125
realistic_Hard,jamba-1.5-large,0,22,0.1094
realistic_Hard,jamba-1.5-large,0,24,0.1016
realistic_Hard,jamba-1.5-large,0,26,0.0781
realistic_Hard,jamba-1.5-large,0,28,0.0859
realistic_Hard,jamba-1.5-large,0,30,0.0938
realistic_Hard,gemini-1.5-flash-002,0,2,0.765
realistic_Hard,gemini-1.5-flash-002,0,3,0.84
realistic_Hard,gemini-1.5-flash-002,0,4,0.77
realistic_Hard,gemini-1.5-flash-002,0,5,0.765
realistic_Hard,gemini-1.5-flash-002,0,6,0.765
realistic_Hard,gemini-1.5-flash-002,0,7,0.76
realistic_Hard,gemini-1.5-flash-002,0,8,0.725
realistic_Hard,gemini-1.5-flash-002,0,9,0.64
realistic_Hard,gemini-1.5-flash-002,0,10,0.63
realistic_Hard,gemini-1.5-flash-002,0,11,0.575
realistic_Hard,gemini-1.5-flash-002,0,12,0.52
realistic_Hard,gemini-1.5-flash-002,0,13,0.45
realistic_Hard,gemini-1.5-flash-002,0,14,0.77
realistic_Hard,gemini-1.5-flash-002,0,15,0.46
realistic_Hard,gemini-1.5-flash-002,0,16,0.455
realistic_Hard,gemini-1.5-flash-002,0,17,0.38
realistic_Hard,gemini-1.5-flash-002,0,18,0.36
realistic_Hard,gemini-1.5-flash-002,0,19,0.415
realistic_Hard,gemini-1.5-flash-002,0,20,0.33
realistic_Hard,gemini-1.5-flash-002,0,21,0.24
realistic_Hard,gemini-1.5-flash-002,0,22,0.19
realistic_Hard,gemini-1.5-flash-002,0,23,0.22
realistic_Hard,gemini-1.5-flash-002,0,24,0.17
realistic_Hard,gemini-1.5-flash-002,0,25,0.165
realistic_Hard,gemini-1.5-flash-002,0,26,0.125
realistic_Hard,gemini-1.5-flash-002,0,27,0.11
realistic_Hard,gemini-1.5-flash-002,0,28,0.12
realistic_Hard,gemini-1.5-flash-002,0,29,0.125
realistic_Hard,gemini-1.5-flash-002,0,30,0.095
realistic_Hard,gemini-1.5-flash-002,0,35,0.0
realistic_Hard,gemini-1.5-flash-002,8000,2,0.7031
realistic_Hard,gemini-1.5-flash-002,8000,4,0.6406
realistic_Hard,gemini-1.5-flash-002,8000,6,0.6406
realistic_Hard,gemini-1.5-flash-002,8000,8,0.5156
realistic_Hard,gemini-1.5-flash-002,8000,10,0.4141
realistic_Hard,gemini-1.5-flash-002,8000,12,0.3438
realistic_Hard,gemini-1.5-flash-002,8000,16,0.25
realistic_Hard,gemini-1.5-flash-002,8000,18,0.1736
realistic_Hard,gemini-1.5-flash-002,8000,20,0.2773
realistic_Hard,gemini-1.5-flash-002,8000,22,0.1339
realistic_Hard,gemini-1.5-flash-002,8000,24,0.1452
realistic_Hard,gemini-1.5-flash-002,8000,26,0.1172
realistic_Hard,gemini-1.5-flash-002,8000,28,0.129
realistic_Hard,gemini-1.5-flash-002,8000,30,0.0938
realistic_Hard,gemini-1.5-flash-002,16000,2,0.6094
realistic_Hard,gemini-1.5-flash-002,16000,4,0.5938
realistic_Hard,gemini-1.5-flash-002,16000,6,0.5469
realistic_Hard,gemini-1.5-flash-002,16000,8,0.4062
realistic_Hard,gemini-1.5-flash-002,16000,10,0.3125
realistic_Hard,gemini-1.5-flash-002,16000,12,0.3047
realistic_Hard,gemini-1.5-flash-002,16000,14,0.1719
realistic_Hard,gemini-1.5-flash-002,16000,16,0.0859
realistic_Hard,gemini-1.5-flash-002,16000,18,0.0781
realistic_Hard,gemini-1.5-flash-002,16000,20,0.0703
realistic_Hard,gemini-1.5-flash-002,16000,22,0.0312
realistic_Hard,gemini-1.5-flash-002,16000,24,0.0547
realistic_Hard,gemini-1.5-flash-002,16000,26,0.0391
realistic_Hard,gemini-1.5-flash-002,16000,28,0.0234
realistic_Hard,gemini-1.5-flash-002,16000,30,0.0312
realistic_Hard,gemini-1.5-flash-002,32000,2,0.6406
realistic_Hard,gemini-1.5-flash-002,32000,4,0.5
realistic_Hard,gemini-1.5-flash-002,32000,6,0.4844
realistic_Hard,gemini-1.5-flash-002,32000,8,0.3047
realistic_Hard,gemini-1.5-flash-002,32000,10,0.2109
realistic_Hard,gemini-1.5-flash-002,32000,12,0.1641
realistic_Hard,gemini-1.5-flash-002,32000,14,0.1406
realistic_Hard,gemini-1.5-flash-002,32000,16,0.1094
realistic_Hard,gemini-1.5-flash-002,32000,18,0.0391
realistic_Hard,gemini-1.5-flash-002,32000,20,0.0703
realistic_Hard,gemini-1.5-flash-002,32000,22,0.0394
realistic_Hard,gemini-1.5-flash-002,32000,24,0.0078
realistic_Hard,gemini-1.5-flash-002,32000,26,0.0078
realistic_Hard,gemini-1.5-flash-002,32000,28,0.0157
realistic_Hard,gemini-1.5-flash-002,32000,30,0.0156
realistic_Hard,qwq-32b-preview,0,2,0.655
realistic_Hard,qwq-32b-preview,0,3,0.72
realistic_Hard,qwq-32b-preview,0,4,0.775
realistic_Hard,qwq-32b-preview,0,5,0.73
realistic_Hard,qwq-32b-preview,0,6,0.655
realistic_Hard,qwq-32b-preview,0,7,0.72
realistic_Hard,qwq-32b-preview,0,8,0.715
realistic_Hard,qwq-32b-preview,0,9,0.725
realistic_Hard,qwq-32b-preview,0,10,0.64
realistic_Hard,qwq-32b-preview,0,11,0.58
realistic_Hard,qwq-32b-preview,0,12,0.565
realistic_Hard,qwq-32b-preview,0,13,0.515
realistic_Hard,qwq-32b-preview,0,14,0.615
realistic_Hard,qwq-32b-preview,0,15,0.535
realistic_Hard,qwq-32b-preview,0,16,0.57
realistic_Hard,qwq-32b-preview,0,17,0.59
realistic_Hard,qwq-32b-preview,0,18,0.615
realistic_Hard,qwq-32b-preview,0,19,0.545
realistic_Hard,qwq-32b-preview,0,20,0.595
realistic_Hard,qwq-32b-preview,0,21,0.425
realistic_Hard,qwq-32b-preview,0,22,0.41
realistic_Hard,qwq-32b-preview,0,23,0.315
realistic_Hard,qwq-32b-preview,0,24,0.385
realistic_Hard,qwq-32b-preview,0,25,0.36
realistic_Hard,qwq-32b-preview,0,26,0.37
realistic_Hard,qwq-32b-preview,0,27,0.35
realistic_Hard,qwq-32b-preview,0,28,0.35
realistic_Hard,qwq-32b-preview,0,29,0.39
realistic_Hard,qwq-32b-preview,0,30,0.255
realistic_Hard,qwq-32b-preview,0,35,0.20625
realistic_Hard,qwq-32b-preview,0,40,0.125
realistic_Hard,qwq-32b-preview,0,45,0.14375
realistic_Hard,qwq-32b-preview,0,50,0.09375
realistic_Medium,deepseek-v3,0,2,0.945
realistic_Medium,deepseek-v3,0,3,0.895
realistic_Medium,deepseek-v3,0,4,0.965
realistic_Medium,deepseek-v3,0,5,0.965
realistic_Medium,deepseek-v3,0,6,0.965
realistic_Medium,deepseek-v3,0,7,0.935
realistic_Medium,deepseek-v3,0,8,0.875
realistic_Medium,deepseek-v3,0,9,0.97
realistic_Medium,deepseek-v3,0,10,0.81
realistic_Medium,deepseek-v3,0,11,0.87
realistic_Medium,deepseek-v3,0,12,0.715
realistic_Medium,deepseek-v3,0,13,0.735
realistic_Medium,deepseek-v3,0,14,0.785
realistic_Medium,deepseek-v3,0,15,0.825
realistic_Medium,deepseek-v3,0,16,0.585
realistic_Medium,deepseek-v3,0,17,0.605
realistic_Medium,deepseek-v3,0,18,0.71
realistic_Medium,deepseek-v3,0,19,0.565
realistic_Medium,deepseek-v3,0,20,0.625
realistic_Medium,deepseek-v3,0,21,0.625
realistic_Medium,deepseek-v3,0,22,0.67
realistic_Medium,deepseek-v3,0,24,0.7
realistic_Medium,deepseek-v3,0,25,0.62
realistic_Medium,deepseek-v3,0,26,0.715
realistic_Medium,deepseek-v3,0,27,0.665
realistic_Medium,deepseek-v3,0,28,0.63
realistic_Medium,deepseek-v3,0,29,0.655
realistic_Medium,deepseek-v3,0,30,0.635
realistic_Medium,deepseek-v3,0,35,0.5625
realistic_Medium,deepseek-v3,0,40,0.5625
realistic_Medium,deepseek-v3,0,45,0.5
realistic_Medium,deepseek-v3,0,50,0.3625
realistic_Medium,deepseek-v3,0,55,0.39375
realistic_Medium,deepseek-v3,0,60,0.36875
realistic_Medium,deepseek-v3,0,65,0.2625
realistic_Medium,deepseek-v3,0,70,0.1875
realistic_Medium,deepseek-v3,0,75,0.175
realistic_Medium,deepseek-v3,0,80,0.10625
realistic_Medium,deepseek-v3,0,85,0.075
realistic_Medium,deepseek-v3,0,90,0.08125
realistic_Medium,deepseek-v3,0,95,0.03125
realistic_Medium,deepseek-v3,8000,2,0.69
realistic_Medium,deepseek-v3,8000,4,0.865
realistic_Medium,deepseek-v3,8000,6,0.72
realistic_Medium,deepseek-v3,8000,8,0.62
realistic_Medium,deepseek-v3,8000,10,0.4925
realistic_Medium,deepseek-v3,8000,12,0.44
realistic_Medium,deepseek-v3,8000,14,0.29
realistic_Medium,deepseek-v3,8000,16,0.2121
realistic_Medium,deepseek-v3,8000,18,0.205
realistic_Medium,deepseek-v3,8000,20,0.191
realistic_Medium,deepseek-v3,8000,22,0.155
realistic_Medium,deepseek-v3,8000,24,0.13
realistic_Medium,deepseek-v3,8000,26,0.1307
realistic_Medium,deepseek-v3,8000,28,0.13
realistic_Medium,deepseek-v3,8000,30,0.17
realistic_Medium,deepseek-v3,16000,2,0.637056
realistic_Medium,deepseek-v3,16000,4,0.805
realistic_Medium,deepseek-v3,16000,6,0.66
realistic_Medium,deepseek-v3,16000,8,0.405
realistic_Medium,deepseek-v3,16000,10,0.355
realistic_Medium,deepseek-v3,16000,14,0.0894
realistic_Medium,deepseek-v3,16000,16,0.1154
realistic_Medium,deepseek-v3,16000,18,0.073
realistic_Medium,deepseek-v3,16000,20,0.0636
realistic_Medium,deepseek-v3,16000,22,0.07
realistic_Medium,deepseek-v3,16000,24,0.0452
realistic_Medium,deepseek-v3,16000,26,0.035
realistic_Medium,deepseek-v3,16000,28,0.0302
realistic_Medium,deepseek-v3,16000,30,0.025
realistic_Medium,deepseek-v3,32000,2,0.565
realistic_Medium,deepseek-v3,32000,4,0.7342
realistic_Medium,deepseek-v3,32000,6,0.5333
realistic_Medium,deepseek-v3,32000,8,0.3662
realistic_Medium,deepseek-v3,32000,10,0.1029
realistic_Medium,deepseek-v3,32000,12,0.16
realistic_Medium,deepseek-v3,32000,14,0.1443
realistic_Medium,deepseek-v3,32000,16,0.0443
realistic_Medium,deepseek-v3,32000,18,0.05
realistic_Medium,deepseek-v3,32000,20,0.0452
realistic_Medium,deepseek-v3,32000,22,0.035
realistic_Medium,deepseek-v3,32000,24,0.015
realistic_Medium,deepseek-v3,32000,26,0.02
realistic_Medium,deepseek-v3,32000,28,0.05
realistic_Medium,deepseek-v3,32000,30,0.04
symbolic,deepseek-r1,0,1,1.0
symbolic,deepseek-r1,0,21,0.92
symbolic,deepseek-r1,0,41,0.68
symbolic,deepseek-r1,0,61,0.46
symbolic,deepseek-r1,0,81,0.32
symbolic,deepseek-r1,0,101,0.16
symbolic,deepseek-r1,0,121,0.16
symbolic,deepseek-r1,0,141,0.12
symbolic,deepseek-r1,0,161,0.16
symbolic,deepseek-r1,0,181,0.04
symbolic,deepseek-r1,0,201,0.04
symbolic,deepseek-r1,0,221,0.0
symbolic,deepseek-r1,0,241,0.04
symbolic,deepseek-r1,0,261,0.02
symbolic,deepseek-r1,0,281,0.04
symbolic,deepseek-r1,8000,1,1.0
symbolic,deepseek-r1,8000,3,0.92
symbolic,deepseek-r1,8000,5,0.82
symbolic,deepseek-r1,8000,7,0.6
symbolic,deepseek-r1,8000,9,0.54
symbolic,deepseek-r1,8000,11,0.32
symbolic,deepseek-r1,8000,13,0.42
symbolic,deepseek-r1,8000,15,0.22
symbolic,deepseek-r1,8000,17,0.26
symbolic,deepseek-r1,8000,19,0.16
symbolic,deepseek-r1,8000,21,0.22
symbolic,deepseek-r1,8000,23,0.06
symbolic,deepseek-r1,8000,25,0.2
symbolic,deepseek-r1,8000,27,0.02
symbolic,deepseek-r1,8000,29,0.04
symbolic,deepseek-r1,8000,31,0.12
symbolic,deepseek-r1,8000,33,0.04
symbolic,deepseek-r1,8000,35,0.06
symbolic,deepseek-r1,8000,37,0.02
symbolic,deepseek-r1,8000,39,0.04
symbolic,deepseek-r1,8000,41,0.02
symbolic,deepseek-r1,16000,1,1.0
symbolic,deepseek-r1,16000,3,0.86
symbolic,deepseek-r1,16000,5,0.54
symbolic,deepseek-r1,16000,7,0.44
symbolic,deepseek-r1,16000,9,0.4
symbolic,deepseek-r1,16000,11,0.28
symbolic,deepseek-r1,16000,13,0.16
symbolic,deepseek-r1,16000,15,0.2
symbolic,deepseek-r1,16000,17,0.06
symbolic,deepseek-r1,16000,19,0.12
symbolic,deepseek-r1,16000,21,0.14
symbolic,deepseek-r1,16000,23,0.08
symbolic,deepseek-r1,16000,25,0.04
symbolic,deepseek-r1,16000,27,0.0
symbolic,deepseek-r1,16000,29,0.02
symbolic,deepseek-r1,32000,1,1.0
symbolic,deepseek-r1,32000,3,0.68
symbolic,deepseek-r1,32000,5,0.54
symbolic,deepseek-r1,32000,7,0.24
symbolic,deepseek-r1,32000,9,0.14
symbolic,deepseek-r1,32000,11,0.16
symbolic,deepseek-r1,32000,13,0.06
symbolic,deepseek-r1,32000,15,0.06
symbolic,deepseek-r1,32000,17,0.02
symbolic,deepseek-r1,32000,19,0.04