排名 模型 得分
🥇
deepseek-r1 DeepSeek · MIT
1341±9.6 91 - 118 3.9K $0.70 / $2.50 64K 1340.541 [1330.3, 1349.4] 25.95 · 不稳 MIT
🥈
gemini-2.0-flash-001 Google · Proprietary
1337±8.7 135 - 156 6.5K $0.10 / $0.40 1M 1337.055 [1328.5, 1345.9] 19.84 · 不稳 Proprietary
🥉
o1-preview OpenAI · Proprietary
1328±5.2 102 - 127 16.8K $15 / $60 Unknown 1328.322 [1323.2, 1333.7] 7.78 · 波动 Proprietary
4
o1-2024-12-17 OpenAI · Proprietary
1325±6.8 88 - 110 10.1K $15 / $60 200K 1324.824 [1319.2, 1332.7] 9.99 · 波动 Proprietary
5
o3-mini-high OpenAI · Proprietary
1308±9.2 133 - 150 3.7K $1.10 / $4.40 200K 1308.441 [1297.3, 1315.8] 28.21 · 不稳 Proprietary
6
qwen2.5-max 阿里巴巴 · Proprietary
1306±6.7 124 - 137 5.5K Free / N/A Unknown 1305.615 [1298.9, 1312.3] 15.13 · 不稳 Proprietary
7
deepseek-v3 DeepSeek · DeepSeek
1296±5.5 136 - 161 11.5K $1.14 / $4.56 Unknown 1296.155 [1290.6, 1301.7] 9.46 · 波动 DeepSeek
8
step-2-16k-exp-202412 阶跃星辰 · Proprietary
1293±8.2 155 - 194 3.0K Free / N/A Unknown 1292.524 [1283.8, 1300.1] 21.14 · 不稳 Proprietary
9
o1-mini OpenAI · Proprietary
1292±4.1 156 - 184 28.8K $1.10 / $4.40 Unknown 1292.041 [1288.0, 1296.3] 4.32 · 稳定 Proprietary
10
qwen-plus-0125 阿里巴巴 · Proprietary
1290±10.6 143 - 180 3.0K $0.40 / $1.20 131.1K 1290.446 [1280.0, 1301.2] 35.29 · 不稳 Proprietary
11
glm-4-plus-0111 智谱 AI · Proprietary
1289±10.4 147 - 183 3.1K Free / N/A Unknown 1289.041 [1279.6, 1300.4] 27.19 · 不稳 Proprietary
12
o3-mini OpenAI · Proprietary
1284±7.2 147 - 170 7.2K $1.10 / $4.40 200K 1283.636 [1276.3, 1290.7] 13.76 · 不稳 Proprietary
13
gemini-2.0-flash-lite-preview-02-05 Google · Proprietary
1282±6.9 141 - 168 6.3K $0.07 / $0.30 1M 1282.244 [1275.5, 1289.3] 14.05 · 不稳 Proprietary
14
yi-lightning 01.AI · Proprietary
1278±5.3 167 - 198 14.4K Free / N/A Unknown 1277.715 [1272.5, 1283.1] 8.40 · 波动 Proprietary
15
qwen2.5-plus-1127 阿里巴巴 · Proprietary
1273±7.6 184 - 217 6.1K Free / N/A Unknown 1273.000 [1264.9, 1280.0] 18.29 · 不稳 Proprietary
16
gemini-1.5-pro-002 Google · Proprietary
1273±4.1 143 - 169 29.4K $3.50 / $10.50 2.1M 1272.641 [1268.9, 1277.2] 4.81 · 稳定 Proprietary
17
grok-2-2024-08-13 xAI · Proprietary
1270±3.6 157 - 186 36.2K $2 / $10 131.1K 1269.658 [1265.8, 1273.1] 4.65 · 稳定 Proprietary
18
llama-3.1-405b-instruct-bf16 Meta · Llama 3.1 Community
1263±5.7 160 - 187 17.4K $4 / $4 32.8K 1263.156 [1258.3, 1269.6] 8.97 · 波动 Llama 3.1 Community
19
llama-3.1-nemotron-70b-instruct NVIDIA · Llama 3.1
1263±10.2 207 - 231 3.9K $1.20 / $1.20 131.1K 1263.042 [1251.4, 1271.7] 25.69 · 不稳 Llama 3.1
20
gpt-4o-2024-05-13 OpenAI · Proprietary
1263±3.5 150 - 173 62.4K $5 / $15 128K 1262.702 [1259.4, 1266.3] 3.29 · 稳定 Proprietary
21
llama-3.1-405b-instruct-fp8 Meta · Llama 3.1 Community
1260±3.9 164 - 188 34.1K $4 / $4 32.8K 1260.149 [1256.5, 1264.2] 4.50 · 稳定 Llama 3.1 Community
22
deepseek-v2.5-1210 DeepSeek · DeepSeek
1259±9.4 171 - 209 4.0K Free / N/A Unknown 1259.433 [1249.6, 1268.3] 25.09 · 不稳 DeepSeek
23
athene-v2-chat NexusFlow · NexusFlow
1257±5.4 187 - 216 14.4K Free / N/A Unknown 1256.873 [1251.9, 1262.7] 8.31 · 波动 NexusFlow
24
claude-3-5-sonnet-20241022 Anthropic · Proprietary
1257±4.0 127 - 138 29.6K $3 / $15 200K 1256.528 [1252.7, 1260.7] 4.37 · 稳定 Proprietary
25
gpt-4o-mini-2024-07-18 OpenAI · Proprietary
1253±3.9 184 - 209 35.4K $0.15 / $0.60 128K 1252.736 [1248.7, 1256.6] 4.22 · 稳定 Proprietary
26
llama-3.3-70b-instruct Meta · Llama-3.3
1252±5.1 184 - 209 14.7K $0.10 / $0.32 131.1K 1252.301 [1247.7, 1257.9] 7.07 · 波动 Llama-3.3
27
grok-2-mini-2024-08-13 xAI · Proprietary
1250±4.4 200 - 220 29.8K $2 / $10 131.1K 1250.208 [1245.0, 1253.8] 4.78 · 稳定 Proprietary
28
glm-4-plus 智谱 AI · Proprietary
1248±5.3 181 - 209 13.9K $0.44 / $1.76 204.8K 1247.646 [1242.3, 1252.9] 8.19 · 波动 Proprietary
29
llama-3.1-70b-instruct Meta · Llama 3.1 Community
1246±4.4 218 - 232 31.3K $0.40 / $0.40 131.1K 1245.770 [1242.0, 1250.9] 4.41 · 稳定 Llama 3.1 Community
30
gpt-4o-2024-08-06 OpenAI · Proprietary
1245±3.8 157 - 187 26.5K $2.50 / $10 128K 1244.946 [1241.6, 1249.1] 4.12 · 稳定 Proprietary
31
qwen-max-0919 阿里巴巴 · Qwen
1244±6.5 181 - 212 8.8K $1.60 / $6.40 32.8K 1243.619 [1237.9, 1251.0] 12.47 · 不稳 Qwen
32
gemini-1.5-flash-002 Google · Proprietary
1241±5.1 196 - 220 19.4K $0.07 / $0.30 1M 1241.286 [1236.4, 1246.7] 7.09 · 波动 Proprietary
33
claude-3-5-sonnet-20240620 Anthropic · Proprietary
1241±4.1 152 - 179 46.2K $3 / $15 200K 1241.038 [1236.7, 1244.8] 4.10 · 稳定 Proprietary
34
gpt-4-turbo-2024-04-09 OpenAI · Proprietary
1241±3.3 179 - 205 56.9K $10 / $30 128K 1240.937 [1237.8, 1244.4] 3.56 · 稳定 Proprietary
35
deepseek-v2.5 DeepSeek · DeepSeek
1238±5.6 201 - 221 13.7K Free / N/A Unknown 1238.383 [1232.9, 1244.0] 10.03 · 波动 DeepSeek
36
mistral-large-2407 Mistral · Mistral Research
1238±4.0 189 - 216 26.1K $2 / $6 131.1K 1238.381 [1234.5, 1242.6] 4.18 · 稳定 Mistral Research
37
athene-70b-0725 NexusFlow · CC-BY-NC-4.0
1238±5.0 201 - 221 11.8K Free / N/A Unknown 1237.891 [1233.8, 1243.8] 7.86 · 波动 CC-BY-NC-4.0
38
qwen2.5-72b-instruct 阿里巴巴 · Qwen
1236±4.5 207 - 221 21.6K $1.20 / $1.20 Unknown 1236.319 [1232.1, 1241.1] 5.67 · 波动 Qwen
39
gemini-advanced-0514 Google · Proprietary
1234±4.0 157 - 187 27.1K Free / N/A Unknown 1234.224 [1230.3, 1238.3] 4.70 · 稳定 Proprietary
40
mistral-large-2411 Mistral · MRL
1232±5.6 204 - 221 11.9K $2 / $6 131.1K 1231.993 [1226.2, 1237.4] 8.98 · 波动 MRL
41
gpt-4-1106-preview OpenAI · Proprietary
1231±3.3 189 - 217 66.4K $10 / $30 128K 1231.439 [1228.8, 1235.4] 3.40 · 稳定 Proprietary
42
gemini-1.5-pro-001 Google · Proprietary
1231±3.3 179 - 205 44.0K $3.50 / $10.50 2.1M 1231.117 [1228.2, 1234.8] 3.36 · 稳定 Proprietary
43
amazon-nova-pro-v1.0 Amazon · Proprietary
1230±6.5 218 - 233 10.2K $0.80 / $3.20 300K 1230.408 [1224.9, 1237.9] 11.79 · 波动 Proprietary
44
gpt-4-0125-preview OpenAI · Proprietary
1226±3.4 189 - 217 56.7K $10 / $30 128K 1226.165 [1223.3, 1230.1] 3.21 · 稳定 Proprietary
45
llama-3-70b-instruct Meta · Llama 3 Community
1226±2.8 229 - 242 93.7K $0.51 / $0.74 8.2K 1226.095 [1223.7, 1229.3] 2.61 · 稳定 Llama 3 Community
46
llama-3.1-tulu-3-70b Allen AI · Llama 3.1
1224±14.5 218 - 242 1.7K Free / N/A Unknown 1224.324 [1210.8, 1239.8] 56.34 · 不稳 Llama 3.1
47
jamba-1.5-large AI21 Labs · Jamba Open
1218±8.3 218 - 236 5.1K $2 / $8 256K 1217.530 [1208.8, 1225.4] 19.67 · 不稳 Jamba Open
48
llama-3.1-nemotron-51b-instruct NVIDIA · Llama 3.1
1216±13.0 218 - 242 1.9K Free / N/A Unknown 1216.444 [1202.5, 1228.6] 48.02 · 不稳 Llama 3.1
49
claude-3-opus-20240229 Anthropic · Proprietary
1214±2.9 181 - 206 112.0K $15 / $75 200K 1213.668 [1210.5, 1216.4] 2.70 · 稳定 Proprietary
50
claude-3-5-haiku-20241022 Anthropic · Proprietary
1214±6.2 179 - 205 12.0K $0.80 / $4 200K 1213.668 [1207.8, 1220.3] 10.44 · 波动 Proprietary
51
reka-core-20240904 Reka AI · Proprietary
1208±9.3 218 - 236 4.3K Free / N/A Unknown 1208.276 [1200.2, 1218.8] 21.40 · 不稳 Proprietary
52
qwen2.5-coder-32b-instruct 阿里巴巴 · Apache 2.0
1202±10.2 231 - 251 2.8K $0.87 / $0.87 32K 1201.649 [1190.3, 1210.6] 28.58 · 不稳 Apache 2.0
53
gemini-1.5-flash-001 Google · Proprietary
1200±3.5 221 - 236 35.0K $0.07 / $0.30 1M 1200.174 [1197.4, 1204.3] 3.70 · 稳定 Proprietary
54
mistral-small-24b-instruct-2501 Mistral · Apache 2.0
1199±9.4 229 - 245 3.7K $0.05 / $0.08 32.8K 1199.315 [1190.4, 1209.1] 22.88 · 不稳 Apache 2.0
55
amazon-nova-lite-v1.0 Amazon · Proprietary
1197±6.2 241 - 253 9.0K $0.06 / $0.24 300K 1196.702 [1191.0, 1203.4] 10.46 · 波动 Proprietary
56
gemma-2-9b-it-simpo Princeton · MIT
1196±6.3 222 - 242 6.1K $0.03 / $0.09 8.2K 1195.797 [1189.4, 1202.0] 11.05 · 波动 MIT
57
gemma-2-27b-it Google · Gemma license
1195±3.9 220 - 233 42.0K $0.65 / $0.65 8.2K 1195.046 [1190.9, 1198.6] 4.03 · 稳定 Gemma license
58
glm-4-0520 智谱 AI · Proprietary
1190±7.3 229 - 246 5.3K Free / N/A Unknown 1190.179 [1182.8, 1197.4] 15.35 · 不稳 Proprietary
59
command-r-plus-08-2024 Cohere · CC-BY-NC-4.0
1189±7.7 225 - 245 5.7K $2.50 / $10 128K 1189.282 [1182.1, 1197.4] 16.80 · 不稳 CC-BY-NC-4.0
60
nemotron-4-340b-instruct NVIDIA · NVIDIA Open Model
1187±6.4 225 - 243 10.6K Free / N/A Unknown 1186.546 [1180.5, 1193.2] 10.05 · 波动 NVIDIA Open Model
61
gemini-1.5-flash-8b-001 Google · Proprietary
1183±4.7 242 - 253 19.5K $0.07 / $0.30 1M 1182.522 [1178.3, 1187.8] 6.89 · 波动 Proprietary
62
phi-4 Microsoft · MIT
1181±6.7 245 - 253 7.7K $0.07 / $0.14 16.4K 1180.979 [1174.1, 1187.6] 10.72 · 波动 MIT
63
c4ai-aya-expanse-32b Cohere · CC-BY-NC-4.0
1180±5.3 236 - 251 15.1K Free / N/A Unknown 1180.110 [1174.8, 1185.4] 7.24 · 波动 CC-BY-NC-4.0
64
jamba-1.5-mini AI21 Labs · Jamba Open
1178±8.6 252 - 265 5.3K $0.20 / $0.40 256K 1177.616 [1167.9, 1185.1] 20.44 · 不稳 Jamba Open
65
reka-flash-20240904 Reka AI · Proprietary
1177±8.1 229 - 248 4.3K Free / N/A Unknown 1176.776 [1169.2, 1185.4] 17.20 · 不稳 Proprietary
66
amazon-nova-micro-v1.0 Amazon · Proprietary
1177±5.4 252 - 262 9.1K $0.04 / $0.14 128K 1176.677 [1171.3, 1182.1] 9.60 · 波动 Proprietary
67
claude-3-sonnet-20240229 Anthropic · Proprietary
1175±3.1 225 - 242 62.7K $3 / $15 200K 1175.091 [1172.1, 1178.3] 3.20 · 稳定 Proprietary
68
llama-3.1-8b-instruct Meta · Llama 3.1 Community
1171±4.4 270 - 277 28.0K $0.02 / $0.05 16.4K 1171.414 [1168.1, 1176.9] 5.03 · 波动 Llama 3.1 Community
69
qwen2-72b-instruct 阿里巴巴 · Qianwen LICENSE
1171±4.2 240 - 252 20.5K $0.90 / $0.90 32.8K 1170.956 [1167.0, 1175.5] 5.71 · 波动 Qianwen LICENSE
70
hunyuan-standard-256k 腾讯 · Proprietary
1170±14.5 252 - 272 1.3K Free / N/A Unknown 1170.102 [1158.7, 1187.6] 59.50 · 不稳 Proprietary
71
gemma-2-9b-it Google · Gemma license
1170±4.1 238 - 251 30.0K $0.03 / $0.09 8.2K 1169.721 [1165.5, 1173.7] 3.92 · 稳定 Gemma license
72
llama-3.1-tulu-3-8b Allen AI · Llama 3.1
1169±11.3 257 - 276 1.7K Free / N/A Unknown 1169.005 [1157.5, 1180.1] 32.35 · 不稳 Llama 3.1
73
ministral-8b-2410 Mistral · MRL
1167±8.5 252 - 269 2.4K $0.10 / $0.10 131.1K 1167.405 [1158.5, 1175.5] 30.20 · 不稳 MRL
74
gpt-4-0314 OpenAI · Proprietary
1164±3.9 220 - 236 36.4K $30 / $60 8.2K 1164.256 [1160.3, 1168.0] 4.07 · 稳定 Proprietary
75
llama-3-8b-instruct Meta · Llama 3 Community
1164±3.1 261 - 272 63.7K $0.03 / $0.04 8.2K 1163.533 [1160.6, 1166.8] 2.91 · 稳定 Llama 3 Community
76
yi-1.5-34b-chat 01.AI · Apache-2.0
1163±5.9 268 - 277 12.9K Free / N/A Unknown 1163.082 [1156.5, 1168.3] 8.32 · 波动 Apache-2.0
77
command-r-plus Cohere · CC-BY-NC-4.0
1163±3.6 241 - 252 43.9K $2.50 / $10 128K 1162.893 [1159.8, 1167.0] 3.47 · 稳定 CC-BY-NC-4.0
78
claude-3-haiku-20240307 Anthropic · Proprietary
1157±3.5 242 - 252 66.6K $0.25 / $1.25 200K 1157.297 [1153.3, 1160.3] 3.23 · 稳定 Proprietary
79
internlm2_5-20b-chat InternLM · Other
1157±7.3 275 - 294 5.3K $0 / $0 32.8K 1156.721 [1149.4, 1164.0] 17.38 · 不稳 Other
80
command-r-08-2024 Cohere · CC-BY-NC-4.0
1154±7.3 249 - 258 5.8K $0.15 / $0.60 128K 1154.416 [1148.4, 1162.9] 15.55 · 不稳 CC-BY-NC-4.0
81
qwen1.5-110b-chat 阿里巴巴 · Qianwen LICENSE
1150±5.5 254 - 269 14.4K Free / N/A Unknown 1150.460 [1145.2, 1156.3] 8.27 · 波动 Qianwen LICENSE
82
c4ai-aya-expanse-8b Cohere · CC-BY-NC-4.0
1150±6.4 257 - 274 5.8K Free / N/A Unknown 1150.456 [1145.2, 1158.0] 12.38 · 不稳 CC-BY-NC-4.0
83
deepseek-coder-v2 DeepSeek · DeepSeek License
1150±5.5 238 - 252 8.4K $0.14 / $0.28 128K 1149.895 [1144.0, 1155.0] 10.38 · 波动 DeepSeek License
84
gpt-4-0613 OpenAI · Proprietary
1148±3.4 229 - 243 58.8K $30 / $60 8.2K 1147.749 [1144.5, 1151.4] 3.48 · 稳定 Proprietary
85
granite-3.1-8b-instruct IBM · Apache 2.0
1146±13.6 267 - 283 1.9K Free / N/A Unknown 1146.007 [1132.3, 1159.6] 49.33 · 不稳 Apache 2.0
86
mistral-large-2402 Mistral · Proprietary
1146±3.4 252 - 262 38.0K $4 / $12 32K 1145.975 [1142.6, 1149.5] 3.83 · 稳定 Proprietary
87
llama-3.2-3b-instruct Meta · Llama 3.2
1141±10.0 287 - 308 4.4K $0.05 / $0.34 80K 1140.847 [1130.5, 1150.4] 22.66 · 不稳 Llama 3.2
88
qwq-32b-preview 阿里巴巴 · Apache 2.0
1139±12.5 292 - 318 1.9K $0.15 / $0.58 131.1K 1139.408 [1126.6, 1151.5] 44.50 · 不稳 Apache 2.0

没有找到相关模型