feat: update 4 models and release a test set (#6)

- feat: update 4 models and release a test set (582d3c2139f1a4582f5a2f2b7cdb103f5a0faa31)


Co-authored-by: Ren Jiaxi <[email protected]>

app.py

@@ -46,7 +46,7 @@ _BIBTEX = """
 }
 """
 
-_LAST_UPDATED = "December 28, 2024"
+_LAST_UPDATED = "April 13, 2025"
 
 banner_url = "./assets/logo.png"
 _BANNER = f'<div style="display: flex; justify-content: space-around;"><img src="{banner_url}" alt="Banner" style="width: 40vw; min-width: 300px; max-width: 600px;"> </div>'  # noqa

assets/text.py

@@ -11,7 +11,7 @@ on the content safety of LLMs for Chinese (Mandarin).
 To align with the regulations for Chinese Internet content moderation, our ChineseSafe contains 205,034 examples
 across 4 classes and 10 sub-classes of safety issues. For Chinese contexts, we add several special types of illegal content: political sensitivity, pornography,
 and variant/homophonic words. In particular, the benchmark is constructed as a balanced dataset, containing safe and unsafe data collected from internet resources and public datasets [1,2,3].
-We hope the evaluation can provides a guideline for developers and researchers to facilitate the safety of LLMs. <br>  
+We hope the evaluation can provides a guideline for developers and researchers to facilitate the safety of LLMs. A publicly accessible test set comprising 20,000 examples is released at <a href="https://huggingface.co/datasets/SUSTech/ChineseSafe" target="_blank">ChineseSafe</a>.<br>  
 
 The leadboard is under construction and maintained by <a href="https://hongxin001.github.io/" target="_blank">Hongxin Wei's</a> research group at SUSTech.
 Comments, issues, contributions, and collaborations are all welcomed!

changelog.md

@@ -41,4 +41,15 @@ version: v1.0.4
         - Phi-3-small-8k-instruct
         - Phi-3-small-128k-instruct
         - Phi-3-medium-4k-instruct
-        - Phi-3-medium-128k-instruct
+        - Phi-3-medium-128k-instruct
+
+### 2025-4-13
+version: v1.0.5
+
+    changed:
+    - [1]feat: update 4 models due to the February's todo-list:
+        - phi-4
+        - DeepSeek-R1-Distill-Llama-70B
+        - Mistral-Small-24B-Instruct-2501
+        - Moonlight-16B-A3B-Instruct
+    - [2]feat: release a test set of 20000 samples

data/chinese_benchmark_gen.csv

@@ -3,14 +3,17 @@ DeepSeek-LLM-67B-Chat	>65B	76.76/0.35	73.40/0.37	84.26/0.40	81.34/0.35	69.19/0.6
 Llama3-ChatQA-1.5-70B	>65B	65.29/0.29	66.24/0.50	62.92/0.12	64.43/0.19	67.69/0.63
 Qwen2.5-72B-Instruct	>65B	63.41/0.77	66.00/0.95	56.00/0.62	61.49/0.65	70.90/0.96
 Qwen1.5-72B-Chat	>65B	62.91/0.50	73.86/0.84	40.46/0.97	58.75/0.35	85.55/0.62
-Qwen2-72B-Instruct	>65B	54.08/0.20	58.10/0.60	30.72/0.45	52.63/0.05	77.65/0.36
 Opt-66B	>65B	54.46/0.17	53.22/0.06	76.94/0.24	57.73/0.49	31.77/0.28
+Qwen2-72B-Instruct	>65B	54.08/0.20	58.10/0.60	30.72/0.45	52.63/0.05	77.65/0.36
+DeepSeek-R1-Distill-Llama-70B	>65B	52.93/0.18	59.69/0.47	19.33/0.38	51.62/0.16	86.83/0.18
 Llama-3.1-70B-Instruct	>65B	52.84/0.38	59.07/1.22	19.82/0.85	51.57/0.24	86.14/0.58
 Llama-3.3-70B-Instruct	>65B	50.87/0.07	54.51/0.86	13.19/0.10	50.37/0.06	88.89/0.39
 Qwen2.5-32B-Instruct	~30B	69.64/0.39	92.13/0.45	43.24/0.83	62.70/0.25	96.27/0.20
 QwQ-32B-Preview	~30B	69.55/0.28	75.97/0.48	57.60/0.27	65.61/0.17	81.62/0.33
+Mistral-Small-24B-Instruct-2501	~30B	64.48/0.17	64.61/0.35	64.71/0.72	64.34/0.00	64.23/1.04
 Yi-1.5-34B-Chat	~30B	60.06/0.43	58.14/0.40	72.51/0.55	63.27/0.56	47.56/0.42
 Opt-30B	~30B	50.88/0.11	50.76/0.12	72.95/0.16	51.18/0.26	28.62/0.28
+phi-4	10B~20B	72.24/0.24	76.59/0.46	64.42/0.51	69.06/0.15	80.13/0.62
 InternLM2-Chat-20B	10B~20B	70.21/0.55	73.30/0.70	63.79/0.43	67.82/0.45	76.65/0.67
 Qwen1.5-14B-Chat	10B~20B	68.25/0.44	65.87/0.37	76.02/0.72	71.51/0.59	60.44/0.20
 Phi-3-medium-128k-instruct	10B~20B	64.30/0.06	63.89/0.13	66.53/0.52	64.76/0.26	62.05/0.42
@@ -19,6 +22,7 @@ Mistral-Nemo-Instruct-2407	10B~20B	59.71/0.45	61.79/0.52	51.82/0.48	58.20/0.44	6
 Phi-3-medium-4k-instruct	10B~20B	57.79/0.45	58.69/0.37	53.88/0.62	57.02/0.55	61.74/0.55
 Ziya2-13B-Chat	10B~20B	53.40/0.43	53.33/0.38	56.18/0.41	53.48/0.53	50.62/0.61
 Opt-13B	10B~20B	50.18/0.26	50.29/0.20	69.97/0.37	49.94/0.47	30.22/0.31
+Moonlight-16B-A3B-Instruct	10B~20B	45.16/0.43	44.16/0.64	34.79/0.67	45.82/0.33	55.62/0.35
 Phi-3-small-8k-instruct	5B~10B	72.73/0.47	73.67/0.63	71.12/0.49	71.85/0.35	74.36/0.59
 Gemma-1.1-7B-it	5B~10B	71.70/0.26	68.66/0.37	80.11/0.05	76.00/0.09	63.26/0.47
 DeepSeek-LLM-7B-Chat	5B~10B	71.63/0.17	69.50/0.15	77.33/0.67	74.33/0.41	65.90/0.38

data/chinese_benchmark_per.csv

@@ -4,6 +4,7 @@ Qwen1.5-72B-Chat	>65B	63.67/0.46	58.27/0.32	96.84/0.13	90.51/0.57	30.34/0.80
 Qwen2.5-72B-Instruct	>65B	63.27/0.52	66.00/0.60	55.09/0.82	61.31/0.46	71.49/0.25
 Qwen2-72B-Instruct	>65B	60.70/0.49	57.90/0.42	79.03/0.63	66.75/0.77	42.28/0.43
 Opt-66B	>65B	59.93/0.41	56.52/0.37	86.87/0.59	71.36/0.78	32.86/0.74
+DeepSeek-R1-Distill-Llama-70B	>65B	47.68/0.64	45.77/1.21	23.85/0.67	48.35/0.46	71.62/0.60
 Llama-3.1-70B-Instruct	>65B	43.68/0.41	36.45/0.84	16.66/0.34	45.83/0.30	70.82/0.48
 Llama3-ChatQA-1.5-70B	>65B	40.41/0.29	33.86/0.75	19.84/0.75	43.13/0.25	61.08/0.37
 Llama-3.3-70B-Instruct	>65B	36.84/0.82	32.02/1.29	23.19/1.13	39.58/0.63	50.55/0.69
@@ -15,10 +16,13 @@ Phi-3-medium-4k-instruct	10B~20B	71.04/0.31	69.74/0.29	74.56/0.97	72.54/0.59	67.
 Baichuan2-13B-Chat	10B~20B	70.43/0.39	65.81/0.38	85.34/0.63	79.02/0.63	55.46/0.47
 Phi-3-medium-128k-instruct	10B~20B	68.87/0.81	68.08/0.51	71.32/1.44	69.75/1.17	66.41/0.57
 Mistral-Nemo-Instruct-2407	10B~20B	66.88/0.46	62.56/0.28	84.42/0.90	75.89/1.13	49.26/0.24
+phi-4	10B~20B	62.62/0.32	63.73/0.41	58.98/0.20	61.66/0.31	66.28/0.78
 Qwen1.5-14B-Chat	10B~20B	61.29/0.40	57.02/0.32	92.43/0.55	79.80/1.05	30.02/0.47
+Mistral-Small-24B-Instruct-2501	10B~20B	59.20/0.46	58.32/0.42	65.16/1.08	60.33/0.56	53.22/0.20
 Ziya2-13B-Chat	10B~20B	55.25/0.26	59.24/0.37	34.30/0.11	53.61/0.26	76.29/0.39
 InternLM2-Chat-20B	10B~20B	53.67/0.16	79.00/0.66	10.30/0.60	51.90/0.11	97.25/0.26
 Opt-13B	10B~20B	49.31/0.31	37.77/3.57	1.76/0.16	49.59/0.23	97.08/0.29
+Moonlight-16B-A3B-Instruct	10B~20B	48.92/0.16	3.46/0.57	0.07/0.01	49.40/0.15	98.00/0.08
 Gemma-1.1-7B-it	5B~10B	64.32/0.68	59.98/0.58	86.60/0.35	75.70/0.80	41.95/0.93
 Qwen1.5-7B-Chat	5B~10B	62.48/0.54	59.06/0.48	81.92/0.50	70.28/0.65	42.96/0.81
 Phi-3-small-128k-instruct	5B~10B	61.76/0.27	60.47/0.16	68.45/0.61	63.46/0.50	55.05/0.61

data/subclass_gen.csv

@@ -7,10 +7,12 @@ Opt-66B,>65B,0.4866,0.482,0.682,0.5174,0.5203,0.7258,0.5579,0.5338,0.8237,0.5646
 Llama3-ChatQA-1.5-70B,>65B,0.6682,0.6617,0.6566,0.6859,0.6932,0.6922,0.6079,0.6187,0.5348,0.6548,0.7024,0.6342,0.6861,0.6945,0.6928,0.7029,0.6853,0.7281,0.6211,0.6242,0.5599,0.6105,0.6189,0.5397,0.7134,0.6873,0.7493,0.59,0.6072,0.4996
 Llama-3.1-70B-Instruct,>65B,0.4845,0.3825,0.0896,0.5771,0.6976,0.3045,0.4546,0.2021,0.0359,0.6067,0.7722,0.3926,0.5946,0.7225,0.3403,0.5904,0.6813,0.3067,0.4817,0.3639,0.0828,0.4760,0.3471,0.0759,0.5340,0.5584,0.1851,0.4837,0.4207,0.1019
 Llama-3.3-70B-Instruct,>65B,0.5045,0.4639,0.0849,0.5211,0.6327,0.1537,0.4943,0.4221,0.0718,0.5173,0.7089,0.1918,0.5728,0.7424,0.2569,0.5775,0.7071,0.2347,0.4964,0.4060,0.0668,0.4960,0.4244,0.0712,0.5183,0.5179,0.1065,0.4820,0.3636,0.0544
+DeepSeek-R1-Distill-Llama-70B,>65B,0.5416,0.5902,0.2095,0.5495,0.6557,0.2531,0.4770,0.3724,0.0843,0.6293,0.7886,0.4361,0.5619,0.6773,0.2789,0.5560,0.6236,0.2398,0.4694,0.2909,0.0598,0.4773,0.3611,0.0813,0.5191,0.5141,0.1569,0.4642,0.3155,0.0650
 Yi-1.5-34B-Chat,~30B,0.66,0.6114,0.8339,0.7311,0.6644,0.9577,0.3309,0.2379,0.1626,0.6958,0.6708,0.8646,0.7046,0.6528,0.9053,0.7084,0.6383,0.9309,0.5928,0.5672,0.6961,0.4467,0.4308,0.3972,0.6956,0.6281,0.9097,0.5182,0.515,0.5425
 Qwen2.5-32B-Instruct,~30B,0.6204,0.8741,0.2629,0.9049,0.9606,0.8489,0.5103,0.5470,0.0453,0.8192,0.9583,0.6983,0.8514,0.9560,0.7445,0.7823,0.9396,0.5931,0.5869,0.8351,0.1922,0.5244,0.6511,0.0699,0.8334,0.9475,0.6950,0.5157,0.6401,0.0644
 Opt-30B,~30B,0.4672,0.4683,0.6648,0.5002,0.5082,0.7109,0.5044,0.4987,0.7354,0.5314,0.5517,0.7422,0.5108,0.5163,0.7304,0.5161,0.5039,0.7618,0.513,0.5009,0.7578,0.4956,0.4908,0.719,0.5119,0.4977,0.7583,0.4958,0.4955,0.7134
 QwQ-32B-Preview,~30B,0.6837,0.7403,0.5470,0.8120,0.8219,0.8084,0.6060,0.6749,0.3914,0.7516,0.8198,0.6977,0.8121,0.8230,0.8081,0.8470,0.8208,0.8801,0.6113,0.6736,0.3973,0.6050,0.6700,0.3873,0.7492,0.7768,0.6783,0.4656,0.3791,0.1124
+Mistral-Small-24B-Instruct-2501,10B~20B,0.6626,0.6491,0.6746,0.7897,0.7347,0.9223,0.3990,0.2824,0.1406,0.7649,0.7465,0.8603,0.7828,0.7326,0.9081,0.8088,0.7280,0.9732,0.6010,0.6001,0.5490,0.4367,0.3723,0.2159,0.7369,0.6906,0.8282,0.4868,0.4773,0.3217
 Baichuan2-13B-Chat,10B~20B,0.6337,0.6402,0.5755,0.7188,0.7164,0.7457,0.5185,0.5189,0.3417,0.7341,0.7487,0.7703,0.7033,0.7091,0.7143,0.6742,0.6712,0.6575,0.5657,0.5728,0.434,0.6151,0.6264,0.5371,0.6515,0.65,0.6089,0.5532,0.5707,0.414
 Qwen1.5-14B-Chat,10B~20B,0.7099,0.6657,0.8141,0.7897,0.7205,0.9615,0.5669,0.5657,0.5226,0.7776,0.7373,0.9181,0.7571,0.7073,0.897,0.7862,0.7044,0.97,0.6421,0.6225,0.6757,0.5014,0.4893,0.3888,0.7563,0.6869,0.9116,0.5499,0.5538,0.4889
 Ziya2-13B-Chat,10B~20B,0.5403,0.5272,0.5731,0.6597,0.6313,0.8034,0.3259,0.2145,0.1373,0.673,0.6631,0.8101,0.6526,0.6282,0.7886,0.5583,0.5437,0.6097,0.3987,0.3541,0.2823,0.529,0.5194,0.5497,0.5377,0.5208,0.5678,0.4567,0.4484,0.4035
@@ -19,6 +21,8 @@ Opt-13B,10B~20B,0.4746,0.4724,0.637,0.5147,0.519,0.7014,0.5146,0.5059,0.7153,0.5
 Mistral-Nemo-Instruct-2407,10B~20B,0.6375,0.6363,0.6018,0.6971,0.6973,0.7214,0.4741,0.4456,0.2722,0.6349,0.6873,0.6041,0.7122,0.7067,0.7508,0.7259,0.6960,0.7825,0.5252,0.5197,0.3718,0.4695,0.4343,0.2607,0.6126,0.6117,0.5492,0.4474,0.4009,0.2212
 Phi-3-medium-4k-instruct,10B~20B,0.5533,0.5494,0.4889,0.5385,0.5594,0.4653,0.6034,0.6005,0.5922,0.5418,0.5993,0.4803,0.5866,0.6054,0.5590,0.5815,0.5780,0.5475,0.6178,0.6070,0.6217,0.6437,0.6287,0.6742,0.6028,0.5912,0.5893,0.5057,0.5054,0.3950
 Phi-3-medium-128k-instruct,10B~20B,0.6379,0.6234,0.6581,0.6379,0.6437,0.6554,0.6504,0.6361,0.6823,0.5919,0.6413,0.5687,0.6431,0.6483,0.6654,0.6568,0.6374,0.6958,0.6632,0.6403,0.7087,0.6819,0.6546,0.7465,0.6796,0.6480,0.7433,0.5897,0.5935,0.5592
+phi-4,10B~20B,0.7431,0.7737,0.6700,0.7139,0.7762,0.6194,0.7081,0.7576,0.6003,0.6957,0.7921,0.5974,0.7625,0.8010,0.7146,0.8283,0.8125,0.8440,0.7130,0.7564,0.6083,0.6627,0.7239,0.5074,0.8171,0.8052,0.8213,0.6456,0.7165,0.4768
+Moonlight-16B-A3B-Instruct,10B~20B,0.4432,0.4087,0.3134,0.6335,0.6278,0.6971,0.3356,0.1806,0.0982,0.4713,0.5191,0.3914,0.5555,0.5699,0.5449,0.5349,0.5261,0.5011,0.4096,0.3505,0.2448,0.4197,0.3738,0.2672,0.4127,0.3514,0.2496,0.3428,0.2125,0.1175
 Gemma-1.1-7B-it,5B~10B,0.7849,0.7205,0.9139,0.8081,0.7454,0.9485,0.6024,0.6084,0.5413,0.7854,0.758,0.8894,0.8017,0.7436,0.9353,0.8215,0.7367,0.9884,0.6669,0.6543,0.673,0.5811,0.5858,0.4976,0.7831,0.7167,0.9127,0.6684,0.6638,0.6754
 Qwen1.5-7B-Chat,5B~10B,0.6885,0.6347,0.8535,0.7677,0.6891,0.9938,0.6929,0.6404,0.8588,0.7791,0.7151,0.9869,0.7653,0.6889,0.988,0.7485,0.6659,0.9746,0.684,0.6317,0.8443,0.7267,0.6564,0.929,0.7473,0.662,0.9772,0.5545,0.5496,0.5778
 Yi-1.5-9B-Chat,5B~10B,0.7025,0.6913,0.7058,0.7032,0.7106,0.707,0.4533,0.3925,0.2,0.6546,0.7097,0.6172,0.7209,0.7213,0.7419,0.8197,0.7508,0.9452,0.5595,0.5666,0.4131,0.4342,0.3378,0.1591,0.7626,0.7215,0.8306,0.4057,0.2654,0.1096

data/subclass_per.csv

@@ -7,10 +7,12 @@ Opt-66B,>65B,0.645,0.5831,0.9572,0.3981,0.417,0.4471,0.6667,0.5971,0.9953,0.6232
 Llama3-ChatQA-1.5-70B,>65B,0.3666,0.2082,0.1069,0.339,0.169,0.0752,0.3147,0.0148,0.0059,0.2947,0.075,0.0261,0.7758,0.7167,0.9293,0.5528,0.5482,0.4877,0.3396,0.111,0.0507,0.3207,0.0374,0.0156,0.4392,0.3806,0.2524,0.3214,0.0614,0.0253
 Llama-3.1-70B-Instruct,>65B,0.4670,0.4105,0.2107,0.3766,0.1681,0.0560,0.3856,0.1439,0.0505,0.3460,0.1387,0.0392,0.4036,0.2873,0.1107,0.3872,0.1394,0.0487,0.4967,0.4715,0.2711,0.4070,0.2331,0.0910,0.4985,0.4691,0.2716,0.6337,0.6553,0.5548
 Llama-3.3-70B-Instruct,>65B,0.3996,0.3526,0.2759,0.2923,0.1430,0.0771,0.3029,0.1420,0.0825,0.2624,0.1066,0.0486,0.3657,0.3253,0.2213,0.3305,0.2121,0.1358,0.4583,0.4388,0.3966,0.3156,0.1750,0.1062,0.4510,0.4249,0.3802,0.5813,0.5696,0.6459
+DeepSeek-R1-Distill-Llama-70B,>65B,0.4240,0.2914,0.1265,0.6148,0.6530,0.5255,0.3608,0.0107,0.0033,0.5182,0.5945,0.3588,0.5583,0.5989,0.4156,0.4922,0.4667,0.2664,0.4312,0.3134,0.1401,0.3727,0.0743,0.0243,0.4061,0.2132,0.0844,0.5370,0.5522,0.3638
 Yi-1.5-34B-Chat,~30B,0.7139,0.8341,0.5176,0.7722,0.8735,0.6482,0.475,0.2581,0.0357,0.7162,0.8717,0.5603,0.6206,0.7912,0.353,0.8816,0.8938,0.8601,0.6412,0.7813,0.3672,0.497,0.4306,0.0769,0.8472,0.8832,0.7889,0.4818,0.3646,0.0576
 Qwen2.5-32B-Instruct,~30B,0.6749,0.6366,0.7789,0.7893,0.7099,0.9938,0.4372,0.4025,0.2943,0.7921,0.7323,0.9739,0.7723,0.7036,0.9599,0.7702,0.6873,0.9727,0.5920,0.5774,0.6092,0.4358,0.3969,0.2906,0.7404,0.6695,0.9160,0.4640,0.4506,0.3514
 Opt-30B,~30B,0.5831,0.5754,0.5565,0.3952,0.338,0.1915,0.6784,0.6507,0.7506,0.5798,0.6281,0.5559,0.357,0.2405,0.1185,0.406,0.3224,0.1945,0.6203,0.6061,0.633,0.6188,0.6076,0.6293,0.6031,0.5886,0.5976,0.6244,0.6184,0.6415
 QwQ-32B-Preview,~30B,0.5231,0.5061,0.9839,0.5519,0.5328,1.0000,0.4141,0.4443,0.7537,0.5814,0.5650,0.9989,0.5529,0.5340,0.9993,0.5318,0.5111,0.9993,0.5083,0.4978,0.9542,0.4392,0.4593,0.8080,0.5238,0.5042,0.9922,0.5269,0.5128,0.9743
+Mistral-Small-24B-Instruct-2501,~30B,0.5897,0.5714,0.6393,0.7706,0.6931,0.9888,0.3109,0.1339,0.0727,0.7308,0.6984,0.8887,0.7454,0.6830,0.9385,0.7584,0.6732,0.9835,0.5850,0.5671,0.6297,0.3646,0.2744,0.1803,0.7088,0.6450,0.8855,0.3839,0.3257,0.2233
 Baichuan2-13B-Chat,10B~20B,0.7346,0.6715,0.8932,0.7703,0.7043,0.9491,0.6303,0.6129,0.6785,0.7435,0.7152,0.8777,0.779,0.7088,0.9649,0.7677,0.6883,0.9601,0.6763,0.6388,0.7738,0.6359,0.6149,0.6904,0.7096,0.6554,0.8436,0.7306,0.6762,0.8788
 Qwen1.5-14B-Chat,10B~20B,0.625,0.5683,0.964,0.6549,0.5977,0.9932,0.5983,0.5571,0.9038,0.6561,0.6193,0.9535,0.6592,0.6005,0.9994,0.6382,0.5759,0.9897,0.5579,0.53,0.8275,0.5009,0.4938,0.7077,0.6256,0.566,0.9705,0.6063,0.5643,0.914
 Ziya2-13B-Chat,10B~20B,0.6322,0.6632,0.502,0.381,0.0822,0.0212,0.4263,0.2557,0.086,0.4352,0.4474,0.1651,0.612,0.6721,0.4744,0.812,0.7741,0.8691,0.4904,0.4516,0.2102,0.5309,0.5403,0.2964,0.7186,0.7235,0.6777,0.4811,0.4512,0.2021
@@ -19,6 +21,8 @@ Opt-13B,10B~20B,0.5011,0.0392,0.0015,0.4792,0.0695,0.0018,0.4958,0,0,0.4492,0.23
 Mistral-Nemo-Instruct-2407,10B~20B,0.6992,0.6359,0.8960,0.7518,0.6773,0.9826,0.6421,0.6067,0.7767,0.7290,0.6896,0.9121,0.7377,0.6719,0.9542,0.7482,0.6611,0.9959,0.6396,0.6014,0.7754,0.6045,0.5803,0.7019,0.7246,0.6464,0.9529,0.4910,0.4881,0.4717
 Phi-3-medium-4k-instruct,10B~20B,0.8162,0.7447,0.9484,0.3950,0.2748,0.1126,0.8368,0.7558,0.9878,0.5763,0.6486,0.4809,0.6431,0.6695,0.5981,0.8403,0.7549,0.9973,0.8092,0.7414,0.9343,0.8263,0.7504,0.9679,0.8352,0.7499,0.9896,0.6361,0.6499,0.5818
 Phi-3-medium-128k-instruct,10B~20B,0.8024,0.7318,0.9391,0.3592,0.1596,0.0598,0.8232,0.7434,0.9790,0.5228,0.5910,0.3977,0.5699,0.6022,0.4725,0.8293,0.7436,0.9939,0.7813,0.7222,0.8963,0.8009,0.7328,0.9351,0.8260,0.7393,0.9898,0.6525,0.6565,0.6327
+phi-4,10B~20B,0.6193,0.6166,0.5816,0.4118,0.3517,0.1792,0.7011,0.6785,0.7484,0.7224,0.7291,0.7791,0.6152,0.6372,0.5775,0.7375,0.6960,0.8232,0.5775,0.5779,0.4961,0.6685,0.6560,0.6821,0.7074,0.6752,0.7638,0.4629,0.4356,0.2692
+Moonlight-16B-A3B-Instruct,10B~20B,0.5041,0.0556,0.0006,0.4814,0.0000,0.0000,0.4992,0.0000,0.0000,0.4500,0.1369,0.0016,0.4804,0.0256,0.0007,0.5027,0.0000,0.0000,0.5054,0.0893,0.0020,0.5020,0.0972,0.0014,0.5080,0.0256,0.0007,0.4947,0.0000,0.0000
 Gemma-1.1-7B-it,5B~10B,0.6885,0.6193,0.9389,0.7201,0.6502,0.9795,0.6709,0.6133,0.8985,0.7171,0.6709,0.9421,0.5993,0.5861,0.7426,0.7164,0.634,0.9953,0.6316,0.5872,0.8235,0.5207,0.5098,0.595,0.6874,0.616,0.9415,0.6164,0.5853,0.7856
 Qwen1.5-7B-Chat,5B~10B,0.6415,0.5933,0.8439,0.7295,0.6542,0.9987,0.5495,0.5352,0.6535,0.7415,0.6808,0.9875,0.7286,0.6545,0.9955,0.7167,0.6339,0.9966,0.6122,0.5749,0.784,0.4866,0.4788,0.5265,0.6887,0.6165,0.9449,0.4276,0.4219,0.4072
 Yi-1.5-9B-Chat,5B~10B,0.7089,0.8612,0.4825,0.5418,0.7129,0.1741,0.4846,0.2932,0.0308,0.5376,0.7743,0.2115,0.6185,0.8236,0.3254,0.818,0.9011,0.7057,0.5819,0.7416,0.2207,0.4893,0.3279,0.0365,0.7959,0.8937,0.6572,0.477,0.2414,0.0233