Upload from nightly evaluation run
Browse files- languages.json +2 -2
- models.json +11 -0
- results.json +637 -0
languages.json
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
"family":"Indo-European",
|
| 8 |
"flores_path":"eng_Latn",
|
| 9 |
"fleurs_tag":"en_us",
|
| 10 |
-
"commonvoice_hours":
|
| 11 |
"commonvoice_locale":"en",
|
| 12 |
"in_benchmark":true
|
| 13 |
},
|
|
@@ -6367,7 +6367,7 @@
|
|
| 6367 |
"family":"Indo-European",
|
| 6368 |
"flores_path":null,
|
| 6369 |
"fleurs_tag":null,
|
| 6370 |
-
"commonvoice_hours":2.
|
| 6371 |
"commonvoice_locale":"btv",
|
| 6372 |
"in_benchmark":false
|
| 6373 |
},
|
|
|
|
| 7 |
"family":"Indo-European",
|
| 8 |
"flores_path":"eng_Latn",
|
| 9 |
"fleurs_tag":"en_us",
|
| 10 |
+
"commonvoice_hours":2667.0,
|
| 11 |
"commonvoice_locale":"en",
|
| 12 |
"in_benchmark":true
|
| 13 |
},
|
|
|
|
| 6367 |
"family":"Indo-European",
|
| 6368 |
"flores_path":null,
|
| 6369 |
"fleurs_tag":null,
|
| 6370 |
+
"commonvoice_hours":2.5,
|
| 6371 |
"commonvoice_locale":"btv",
|
| 6372 |
"in_benchmark":false
|
| 6373 |
},
|
models.json
CHANGED
|
@@ -251,5 +251,16 @@
|
|
| 251 |
"type":"Commercial",
|
| 252 |
"license":null,
|
| 253 |
"creation_date":1721260800000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 254 |
}
|
| 255 |
]
|
|
|
|
| 251 |
"type":"Commercial",
|
| 252 |
"license":null,
|
| 253 |
"creation_date":1721260800000
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"id":"qwen\/qwen3-235b-a22b",
|
| 257 |
+
"name":"Qwen3 235B A22B (free)",
|
| 258 |
+
"provider_name":"Qwen",
|
| 259 |
+
"cost":0.0,
|
| 260 |
+
"hf_id":"Qwen\/Qwen3-235B-A22B",
|
| 261 |
+
"size":235093634560.0,
|
| 262 |
+
"type":"Open",
|
| 263 |
+
"license":"Apache 2.0",
|
| 264 |
+
"creation_date":1745712000000
|
| 265 |
}
|
| 266 |
]
|
results.json
CHANGED
|
@@ -15923,5 +15923,642 @@
|
|
| 15923 |
"task":"translation_to",
|
| 15924 |
"metric":"chrf",
|
| 15925 |
"score":0.3184321553
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15926 |
}
|
| 15927 |
]
|
|
|
|
| 15923 |
"task":"translation_to",
|
| 15924 |
"metric":"chrf",
|
| 15925 |
"score":0.3184321553
|
| 15926 |
+
},
|
| 15927 |
+
{
|
| 15928 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 15929 |
+
"bcp_47":"ar",
|
| 15930 |
+
"task":"mmlu",
|
| 15931 |
+
"metric":"accuracy",
|
| 15932 |
+
"score":0.0
|
| 15933 |
+
},
|
| 15934 |
+
{
|
| 15935 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 15936 |
+
"bcp_47":"ar",
|
| 15937 |
+
"task":"translation_from",
|
| 15938 |
+
"metric":"bleu",
|
| 15939 |
+
"score":0.1426801844
|
| 15940 |
+
},
|
| 15941 |
+
{
|
| 15942 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 15943 |
+
"bcp_47":"ar",
|
| 15944 |
+
"task":"translation_from",
|
| 15945 |
+
"metric":"chrf",
|
| 15946 |
+
"score":0.3326263623
|
| 15947 |
+
},
|
| 15948 |
+
{
|
| 15949 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 15950 |
+
"bcp_47":"ar",
|
| 15951 |
+
"task":"translation_to",
|
| 15952 |
+
"metric":"bleu",
|
| 15953 |
+
"score":0.3435811596
|
| 15954 |
+
},
|
| 15955 |
+
{
|
| 15956 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 15957 |
+
"bcp_47":"ar",
|
| 15958 |
+
"task":"translation_to",
|
| 15959 |
+
"metric":"chrf",
|
| 15960 |
+
"score":0.5560665631
|
| 15961 |
+
},
|
| 15962 |
+
{
|
| 15963 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 15964 |
+
"bcp_47":"bn",
|
| 15965 |
+
"task":"mmlu",
|
| 15966 |
+
"metric":"accuracy",
|
| 15967 |
+
"score":0.0
|
| 15968 |
+
},
|
| 15969 |
+
{
|
| 15970 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 15971 |
+
"bcp_47":"bn",
|
| 15972 |
+
"task":"translation_from",
|
| 15973 |
+
"metric":"bleu",
|
| 15974 |
+
"score":0.2276144574
|
| 15975 |
+
},
|
| 15976 |
+
{
|
| 15977 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 15978 |
+
"bcp_47":"bn",
|
| 15979 |
+
"task":"translation_from",
|
| 15980 |
+
"metric":"chrf",
|
| 15981 |
+
"score":0.4138420365
|
| 15982 |
+
},
|
| 15983 |
+
{
|
| 15984 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 15985 |
+
"bcp_47":"bn",
|
| 15986 |
+
"task":"translation_to",
|
| 15987 |
+
"metric":"bleu",
|
| 15988 |
+
"score":0.23060166
|
| 15989 |
+
},
|
| 15990 |
+
{
|
| 15991 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 15992 |
+
"bcp_47":"bn",
|
| 15993 |
+
"task":"translation_to",
|
| 15994 |
+
"metric":"chrf",
|
| 15995 |
+
"score":0.4010315404
|
| 15996 |
+
},
|
| 15997 |
+
{
|
| 15998 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 15999 |
+
"bcp_47":"de",
|
| 16000 |
+
"task":"mmlu",
|
| 16001 |
+
"metric":"accuracy",
|
| 16002 |
+
"score":0.0
|
| 16003 |
+
},
|
| 16004 |
+
{
|
| 16005 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16006 |
+
"bcp_47":"de",
|
| 16007 |
+
"task":"translation_from",
|
| 16008 |
+
"metric":"bleu",
|
| 16009 |
+
"score":0.212111905
|
| 16010 |
+
},
|
| 16011 |
+
{
|
| 16012 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16013 |
+
"bcp_47":"de",
|
| 16014 |
+
"task":"translation_from",
|
| 16015 |
+
"metric":"chrf",
|
| 16016 |
+
"score":0.3988046786
|
| 16017 |
+
},
|
| 16018 |
+
{
|
| 16019 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16020 |
+
"bcp_47":"de",
|
| 16021 |
+
"task":"translation_to",
|
| 16022 |
+
"metric":"bleu",
|
| 16023 |
+
"score":0.3848855202
|
| 16024 |
+
},
|
| 16025 |
+
{
|
| 16026 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16027 |
+
"bcp_47":"de",
|
| 16028 |
+
"task":"translation_to",
|
| 16029 |
+
"metric":"chrf",
|
| 16030 |
+
"score":0.5719833521
|
| 16031 |
+
},
|
| 16032 |
+
{
|
| 16033 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16034 |
+
"bcp_47":"en",
|
| 16035 |
+
"task":"mmlu",
|
| 16036 |
+
"metric":"accuracy",
|
| 16037 |
+
"score":0.0
|
| 16038 |
+
},
|
| 16039 |
+
{
|
| 16040 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16041 |
+
"bcp_47":"en",
|
| 16042 |
+
"task":"translation_from",
|
| 16043 |
+
"metric":"bleu",
|
| 16044 |
+
"score":0.344237678
|
| 16045 |
+
},
|
| 16046 |
+
{
|
| 16047 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16048 |
+
"bcp_47":"en",
|
| 16049 |
+
"task":"translation_from",
|
| 16050 |
+
"metric":"chrf",
|
| 16051 |
+
"score":0.4935151813
|
| 16052 |
+
},
|
| 16053 |
+
{
|
| 16054 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16055 |
+
"bcp_47":"en",
|
| 16056 |
+
"task":"translation_to",
|
| 16057 |
+
"metric":"bleu",
|
| 16058 |
+
"score":0.4698515104
|
| 16059 |
+
},
|
| 16060 |
+
{
|
| 16061 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16062 |
+
"bcp_47":"en",
|
| 16063 |
+
"task":"translation_to",
|
| 16064 |
+
"metric":"chrf",
|
| 16065 |
+
"score":0.6371144417
|
| 16066 |
+
},
|
| 16067 |
+
{
|
| 16068 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16069 |
+
"bcp_47":"es",
|
| 16070 |
+
"task":"mmlu",
|
| 16071 |
+
"metric":"accuracy",
|
| 16072 |
+
"score":0.0
|
| 16073 |
+
},
|
| 16074 |
+
{
|
| 16075 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16076 |
+
"bcp_47":"es",
|
| 16077 |
+
"task":"translation_from",
|
| 16078 |
+
"metric":"bleu",
|
| 16079 |
+
"score":0.125959352
|
| 16080 |
+
},
|
| 16081 |
+
{
|
| 16082 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16083 |
+
"bcp_47":"es",
|
| 16084 |
+
"task":"translation_from",
|
| 16085 |
+
"metric":"chrf",
|
| 16086 |
+
"score":0.3551503278
|
| 16087 |
+
},
|
| 16088 |
+
{
|
| 16089 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16090 |
+
"bcp_47":"es",
|
| 16091 |
+
"task":"translation_to",
|
| 16092 |
+
"metric":"bleu",
|
| 16093 |
+
"score":0.3175303108
|
| 16094 |
+
},
|
| 16095 |
+
{
|
| 16096 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16097 |
+
"bcp_47":"es",
|
| 16098 |
+
"task":"translation_to",
|
| 16099 |
+
"metric":"chrf",
|
| 16100 |
+
"score":0.5762214155
|
| 16101 |
+
},
|
| 16102 |
+
{
|
| 16103 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16104 |
+
"bcp_47":"fr",
|
| 16105 |
+
"task":"mmlu",
|
| 16106 |
+
"metric":"accuracy",
|
| 16107 |
+
"score":0.0
|
| 16108 |
+
},
|
| 16109 |
+
{
|
| 16110 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16111 |
+
"bcp_47":"fr",
|
| 16112 |
+
"task":"translation_from",
|
| 16113 |
+
"metric":"bleu",
|
| 16114 |
+
"score":0.0902044795
|
| 16115 |
+
},
|
| 16116 |
+
{
|
| 16117 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16118 |
+
"bcp_47":"fr",
|
| 16119 |
+
"task":"translation_from",
|
| 16120 |
+
"metric":"chrf",
|
| 16121 |
+
"score":0.2605011709
|
| 16122 |
+
},
|
| 16123 |
+
{
|
| 16124 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16125 |
+
"bcp_47":"fr",
|
| 16126 |
+
"task":"translation_to",
|
| 16127 |
+
"metric":"bleu",
|
| 16128 |
+
"score":0.4870055243
|
| 16129 |
+
},
|
| 16130 |
+
{
|
| 16131 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16132 |
+
"bcp_47":"fr",
|
| 16133 |
+
"task":"translation_to",
|
| 16134 |
+
"metric":"chrf",
|
| 16135 |
+
"score":0.6791559488
|
| 16136 |
+
},
|
| 16137 |
+
{
|
| 16138 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16139 |
+
"bcp_47":"hi",
|
| 16140 |
+
"task":"mmlu",
|
| 16141 |
+
"metric":"accuracy",
|
| 16142 |
+
"score":0.0
|
| 16143 |
+
},
|
| 16144 |
+
{
|
| 16145 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16146 |
+
"bcp_47":"hi",
|
| 16147 |
+
"task":"translation_from",
|
| 16148 |
+
"metric":"bleu",
|
| 16149 |
+
"score":0.2633758754
|
| 16150 |
+
},
|
| 16151 |
+
{
|
| 16152 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16153 |
+
"bcp_47":"hi",
|
| 16154 |
+
"task":"translation_from",
|
| 16155 |
+
"metric":"chrf",
|
| 16156 |
+
"score":0.4288846329
|
| 16157 |
+
},
|
| 16158 |
+
{
|
| 16159 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16160 |
+
"bcp_47":"hi",
|
| 16161 |
+
"task":"translation_to",
|
| 16162 |
+
"metric":"bleu",
|
| 16163 |
+
"score":0.1741929926
|
| 16164 |
+
},
|
| 16165 |
+
{
|
| 16166 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16167 |
+
"bcp_47":"hi",
|
| 16168 |
+
"task":"translation_to",
|
| 16169 |
+
"metric":"chrf",
|
| 16170 |
+
"score":0.3117418002
|
| 16171 |
+
},
|
| 16172 |
+
{
|
| 16173 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16174 |
+
"bcp_47":"id",
|
| 16175 |
+
"task":"mmlu",
|
| 16176 |
+
"metric":"accuracy",
|
| 16177 |
+
"score":0.0
|
| 16178 |
+
},
|
| 16179 |
+
{
|
| 16180 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16181 |
+
"bcp_47":"id",
|
| 16182 |
+
"task":"translation_from",
|
| 16183 |
+
"metric":"bleu",
|
| 16184 |
+
"score":0.1385874564
|
| 16185 |
+
},
|
| 16186 |
+
{
|
| 16187 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16188 |
+
"bcp_47":"id",
|
| 16189 |
+
"task":"translation_from",
|
| 16190 |
+
"metric":"chrf",
|
| 16191 |
+
"score":0.3284698328
|
| 16192 |
+
},
|
| 16193 |
+
{
|
| 16194 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16195 |
+
"bcp_47":"id",
|
| 16196 |
+
"task":"translation_to",
|
| 16197 |
+
"metric":"bleu",
|
| 16198 |
+
"score":0.2276816545
|
| 16199 |
+
},
|
| 16200 |
+
{
|
| 16201 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16202 |
+
"bcp_47":"id",
|
| 16203 |
+
"task":"translation_to",
|
| 16204 |
+
"metric":"chrf",
|
| 16205 |
+
"score":0.452659811
|
| 16206 |
+
},
|
| 16207 |
+
{
|
| 16208 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16209 |
+
"bcp_47":"ja",
|
| 16210 |
+
"task":"mmlu",
|
| 16211 |
+
"metric":"accuracy",
|
| 16212 |
+
"score":0.0
|
| 16213 |
+
},
|
| 16214 |
+
{
|
| 16215 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16216 |
+
"bcp_47":"ja",
|
| 16217 |
+
"task":"translation_from",
|
| 16218 |
+
"metric":"bleu",
|
| 16219 |
+
"score":0.1632177135
|
| 16220 |
+
},
|
| 16221 |
+
{
|
| 16222 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16223 |
+
"bcp_47":"ja",
|
| 16224 |
+
"task":"translation_from",
|
| 16225 |
+
"metric":"chrf",
|
| 16226 |
+
"score":0.3531449142
|
| 16227 |
+
},
|
| 16228 |
+
{
|
| 16229 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16230 |
+
"bcp_47":"ja",
|
| 16231 |
+
"task":"translation_to",
|
| 16232 |
+
"metric":"bleu",
|
| 16233 |
+
"score":0.2119349185
|
| 16234 |
+
},
|
| 16235 |
+
{
|
| 16236 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16237 |
+
"bcp_47":"ja",
|
| 16238 |
+
"task":"translation_to",
|
| 16239 |
+
"metric":"chrf",
|
| 16240 |
+
"score":0.3123591264
|
| 16241 |
+
},
|
| 16242 |
+
{
|
| 16243 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16244 |
+
"bcp_47":"jv",
|
| 16245 |
+
"task":"translation_from",
|
| 16246 |
+
"metric":"bleu",
|
| 16247 |
+
"score":0.1156136731
|
| 16248 |
+
},
|
| 16249 |
+
{
|
| 16250 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16251 |
+
"bcp_47":"jv",
|
| 16252 |
+
"task":"translation_from",
|
| 16253 |
+
"metric":"chrf",
|
| 16254 |
+
"score":0.2195665146
|
| 16255 |
+
},
|
| 16256 |
+
{
|
| 16257 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16258 |
+
"bcp_47":"jv",
|
| 16259 |
+
"task":"translation_to",
|
| 16260 |
+
"metric":"bleu",
|
| 16261 |
+
"score":0.1897770522
|
| 16262 |
+
},
|
| 16263 |
+
{
|
| 16264 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16265 |
+
"bcp_47":"jv",
|
| 16266 |
+
"task":"translation_to",
|
| 16267 |
+
"metric":"chrf",
|
| 16268 |
+
"score":0.4637640103
|
| 16269 |
+
},
|
| 16270 |
+
{
|
| 16271 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16272 |
+
"bcp_47":"mr",
|
| 16273 |
+
"task":"translation_from",
|
| 16274 |
+
"metric":"bleu",
|
| 16275 |
+
"score":0.1903027055
|
| 16276 |
+
},
|
| 16277 |
+
{
|
| 16278 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16279 |
+
"bcp_47":"mr",
|
| 16280 |
+
"task":"translation_from",
|
| 16281 |
+
"metric":"chrf",
|
| 16282 |
+
"score":0.3635453097
|
| 16283 |
+
},
|
| 16284 |
+
{
|
| 16285 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16286 |
+
"bcp_47":"mr",
|
| 16287 |
+
"task":"translation_to",
|
| 16288 |
+
"metric":"bleu",
|
| 16289 |
+
"score":0.1757074235
|
| 16290 |
+
},
|
| 16291 |
+
{
|
| 16292 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16293 |
+
"bcp_47":"mr",
|
| 16294 |
+
"task":"translation_to",
|
| 16295 |
+
"metric":"chrf",
|
| 16296 |
+
"score":0.289700177
|
| 16297 |
+
},
|
| 16298 |
+
{
|
| 16299 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16300 |
+
"bcp_47":"pa",
|
| 16301 |
+
"task":"translation_from",
|
| 16302 |
+
"metric":"bleu",
|
| 16303 |
+
"score":0.3436575025
|
| 16304 |
+
},
|
| 16305 |
+
{
|
| 16306 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16307 |
+
"bcp_47":"pa",
|
| 16308 |
+
"task":"translation_from",
|
| 16309 |
+
"metric":"chrf",
|
| 16310 |
+
"score":0.482656548
|
| 16311 |
+
},
|
| 16312 |
+
{
|
| 16313 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16314 |
+
"bcp_47":"pa",
|
| 16315 |
+
"task":"translation_to",
|
| 16316 |
+
"metric":"bleu",
|
| 16317 |
+
"score":0.099939613
|
| 16318 |
+
},
|
| 16319 |
+
{
|
| 16320 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16321 |
+
"bcp_47":"pa",
|
| 16322 |
+
"task":"translation_to",
|
| 16323 |
+
"metric":"chrf",
|
| 16324 |
+
"score":0.1871385498
|
| 16325 |
+
},
|
| 16326 |
+
{
|
| 16327 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16328 |
+
"bcp_47":"pt",
|
| 16329 |
+
"task":"mmlu",
|
| 16330 |
+
"metric":"accuracy",
|
| 16331 |
+
"score":0.0
|
| 16332 |
+
},
|
| 16333 |
+
{
|
| 16334 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16335 |
+
"bcp_47":"pt",
|
| 16336 |
+
"task":"translation_from",
|
| 16337 |
+
"metric":"bleu",
|
| 16338 |
+
"score":0.139109335
|
| 16339 |
+
},
|
| 16340 |
+
{
|
| 16341 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16342 |
+
"bcp_47":"pt",
|
| 16343 |
+
"task":"translation_from",
|
| 16344 |
+
"metric":"chrf",
|
| 16345 |
+
"score":0.2975718876
|
| 16346 |
+
},
|
| 16347 |
+
{
|
| 16348 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16349 |
+
"bcp_47":"pt",
|
| 16350 |
+
"task":"translation_to",
|
| 16351 |
+
"metric":"bleu",
|
| 16352 |
+
"score":0.3775837608
|
| 16353 |
+
},
|
| 16354 |
+
{
|
| 16355 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16356 |
+
"bcp_47":"pt",
|
| 16357 |
+
"task":"translation_to",
|
| 16358 |
+
"metric":"chrf",
|
| 16359 |
+
"score":0.5791655154
|
| 16360 |
+
},
|
| 16361 |
+
{
|
| 16362 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16363 |
+
"bcp_47":"ru",
|
| 16364 |
+
"task":"mmlu",
|
| 16365 |
+
"metric":"accuracy",
|
| 16366 |
+
"score":0.0
|
| 16367 |
+
},
|
| 16368 |
+
{
|
| 16369 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16370 |
+
"bcp_47":"ru",
|
| 16371 |
+
"task":"translation_from",
|
| 16372 |
+
"metric":"bleu",
|
| 16373 |
+
"score":0.1469881314
|
| 16374 |
+
},
|
| 16375 |
+
{
|
| 16376 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16377 |
+
"bcp_47":"ru",
|
| 16378 |
+
"task":"translation_from",
|
| 16379 |
+
"metric":"chrf",
|
| 16380 |
+
"score":0.3543525231
|
| 16381 |
+
},
|
| 16382 |
+
{
|
| 16383 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16384 |
+
"bcp_47":"ru",
|
| 16385 |
+
"task":"translation_to",
|
| 16386 |
+
"metric":"bleu",
|
| 16387 |
+
"score":0.2601449601
|
| 16388 |
+
},
|
| 16389 |
+
{
|
| 16390 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16391 |
+
"bcp_47":"ru",
|
| 16392 |
+
"task":"translation_to",
|
| 16393 |
+
"metric":"chrf",
|
| 16394 |
+
"score":0.4637758535
|
| 16395 |
+
},
|
| 16396 |
+
{
|
| 16397 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16398 |
+
"bcp_47":"sw",
|
| 16399 |
+
"task":"mmlu",
|
| 16400 |
+
"metric":"accuracy",
|
| 16401 |
+
"score":0.0
|
| 16402 |
+
},
|
| 16403 |
+
{
|
| 16404 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16405 |
+
"bcp_47":"sw",
|
| 16406 |
+
"task":"translation_from",
|
| 16407 |
+
"metric":"bleu",
|
| 16408 |
+
"score":0.1254796913
|
| 16409 |
+
},
|
| 16410 |
+
{
|
| 16411 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16412 |
+
"bcp_47":"sw",
|
| 16413 |
+
"task":"translation_from",
|
| 16414 |
+
"metric":"chrf",
|
| 16415 |
+
"score":0.3282519563
|
| 16416 |
+
},
|
| 16417 |
+
{
|
| 16418 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16419 |
+
"bcp_47":"sw",
|
| 16420 |
+
"task":"translation_to",
|
| 16421 |
+
"metric":"bleu",
|
| 16422 |
+
"score":0.0915983019
|
| 16423 |
+
},
|
| 16424 |
+
{
|
| 16425 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16426 |
+
"bcp_47":"sw",
|
| 16427 |
+
"task":"translation_to",
|
| 16428 |
+
"metric":"chrf",
|
| 16429 |
+
"score":0.3007484482
|
| 16430 |
+
},
|
| 16431 |
+
{
|
| 16432 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16433 |
+
"bcp_47":"te",
|
| 16434 |
+
"task":"mmlu",
|
| 16435 |
+
"metric":"accuracy",
|
| 16436 |
+
"score":0.0
|
| 16437 |
+
},
|
| 16438 |
+
{
|
| 16439 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16440 |
+
"bcp_47":"te",
|
| 16441 |
+
"task":"translation_from",
|
| 16442 |
+
"metric":"bleu",
|
| 16443 |
+
"score":0.2589650486
|
| 16444 |
+
},
|
| 16445 |
+
{
|
| 16446 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16447 |
+
"bcp_47":"te",
|
| 16448 |
+
"task":"translation_from",
|
| 16449 |
+
"metric":"chrf",
|
| 16450 |
+
"score":0.3965279961
|
| 16451 |
+
},
|
| 16452 |
+
{
|
| 16453 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16454 |
+
"bcp_47":"te",
|
| 16455 |
+
"task":"translation_to",
|
| 16456 |
+
"metric":"bleu",
|
| 16457 |
+
"score":0.1905279289
|
| 16458 |
+
},
|
| 16459 |
+
{
|
| 16460 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16461 |
+
"bcp_47":"te",
|
| 16462 |
+
"task":"translation_to",
|
| 16463 |
+
"metric":"chrf",
|
| 16464 |
+
"score":0.315796915
|
| 16465 |
+
},
|
| 16466 |
+
{
|
| 16467 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16468 |
+
"bcp_47":"ur",
|
| 16469 |
+
"task":"translation_from",
|
| 16470 |
+
"metric":"bleu",
|
| 16471 |
+
"score":0.1738304371
|
| 16472 |
+
},
|
| 16473 |
+
{
|
| 16474 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16475 |
+
"bcp_47":"ur",
|
| 16476 |
+
"task":"translation_from",
|
| 16477 |
+
"metric":"chrf",
|
| 16478 |
+
"score":0.402419023
|
| 16479 |
+
},
|
| 16480 |
+
{
|
| 16481 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16482 |
+
"bcp_47":"ur",
|
| 16483 |
+
"task":"translation_to",
|
| 16484 |
+
"metric":"bleu",
|
| 16485 |
+
"score":0.20023176
|
| 16486 |
+
},
|
| 16487 |
+
{
|
| 16488 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16489 |
+
"bcp_47":"ur",
|
| 16490 |
+
"task":"translation_to",
|
| 16491 |
+
"metric":"chrf",
|
| 16492 |
+
"score":0.3992758012
|
| 16493 |
+
},
|
| 16494 |
+
{
|
| 16495 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16496 |
+
"bcp_47":"vi",
|
| 16497 |
+
"task":"mmlu",
|
| 16498 |
+
"metric":"accuracy",
|
| 16499 |
+
"score":0.0
|
| 16500 |
+
},
|
| 16501 |
+
{
|
| 16502 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16503 |
+
"bcp_47":"vi",
|
| 16504 |
+
"task":"translation_from",
|
| 16505 |
+
"metric":"bleu",
|
| 16506 |
+
"score":0.2127933722
|
| 16507 |
+
},
|
| 16508 |
+
{
|
| 16509 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16510 |
+
"bcp_47":"vi",
|
| 16511 |
+
"task":"translation_from",
|
| 16512 |
+
"metric":"chrf",
|
| 16513 |
+
"score":0.4040178087
|
| 16514 |
+
},
|
| 16515 |
+
{
|
| 16516 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16517 |
+
"bcp_47":"vi",
|
| 16518 |
+
"task":"translation_to",
|
| 16519 |
+
"metric":"bleu",
|
| 16520 |
+
"score":0.1091836451
|
| 16521 |
+
},
|
| 16522 |
+
{
|
| 16523 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16524 |
+
"bcp_47":"vi",
|
| 16525 |
+
"task":"translation_to",
|
| 16526 |
+
"metric":"chrf",
|
| 16527 |
+
"score":0.3365920606
|
| 16528 |
+
},
|
| 16529 |
+
{
|
| 16530 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16531 |
+
"bcp_47":"zh",
|
| 16532 |
+
"task":"mmlu",
|
| 16533 |
+
"metric":"accuracy",
|
| 16534 |
+
"score":0.0
|
| 16535 |
+
},
|
| 16536 |
+
{
|
| 16537 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16538 |
+
"bcp_47":"zh",
|
| 16539 |
+
"task":"translation_from",
|
| 16540 |
+
"metric":"bleu",
|
| 16541 |
+
"score":0.1277232373
|
| 16542 |
+
},
|
| 16543 |
+
{
|
| 16544 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16545 |
+
"bcp_47":"zh",
|
| 16546 |
+
"task":"translation_from",
|
| 16547 |
+
"metric":"chrf",
|
| 16548 |
+
"score":0.3405306117
|
| 16549 |
+
},
|
| 16550 |
+
{
|
| 16551 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16552 |
+
"bcp_47":"zh",
|
| 16553 |
+
"task":"translation_to",
|
| 16554 |
+
"metric":"bleu",
|
| 16555 |
+
"score":0.2524023407
|
| 16556 |
+
},
|
| 16557 |
+
{
|
| 16558 |
+
"model":"qwen\/qwen3-235b-a22b",
|
| 16559 |
+
"bcp_47":"zh",
|
| 16560 |
+
"task":"translation_to",
|
| 16561 |
+
"metric":"chrf",
|
| 16562 |
+
"score":0.2849249913
|
| 16563 |
}
|
| 16564 |
]
|