排名 模型 得分
🥇
gemini-3-pro Google · Proprietary
1378±25.8 4 - 10 1.4K $2 / $12 1M 1377.846 [1352.1, 1403.6] 173.11 · 不稳 Proprietary
🥈
gemini-3-flash Google · Proprietary
1335±38.7 8 - 21 332 $0.50 / $3 1M 1335.396 [1296.7, 1374.1] 390.58 · 不稳 Proprietary
🥉
gemini-3-flash (thinking-minimal) Google · Proprietary
1304±41.9 15 - 29 242 $0.50 / $3 1M 1303.537 [1261.6, 1345.4] 456.75 · 不稳 Proprietary
4
gemini-2.5-flash-preview-09-2025 Google · Proprietary
1291±32.4 81 - 107 439 $0.30 / $2.50 1M 1290.651 [1258.3, 1323.0] 272.66 · 不稳 Proprietary
5
gemini-2.5-pro Google · Proprietary
1288±23.8 29 - 47 2.3K $1.25 / $10 1M 1288.097 [1264.3, 1311.8] 146.84 · 不稳 Proprietary
6
qwen3-vl-235b-a22b-instruct 阿里巴巴 · Apache 2.0
1279±29.1 61 - 93 669 $0.20 / $0.88 262.1K 1278.826 [1249.8, 1307.9] 219.76 · 不稳 Apache 2.0
7
gemini-2.5-flash Google · Proprietary
1277±24.5 71 - 96 1.7K $0.30 / $2.50 1M 1277.360 [1252.9, 1301.8] 155.76 · 不稳 Proprietary
8
ernie-5.0-preview-1220 百度 · Proprietary
1275±45.9 196 1275.054 [1229.1, 1321.0] 549.33 · 不稳 Proprietary
9
gpt-5.1-high OpenAI · Proprietary
1272±35.5 21 - 40 360 $1.25 / $10 400K 1271.899 [1236.4, 1307.4] 327.59 · 不稳 Proprietary
10
gpt-5.1 OpenAI · Proprietary
1268±31.9 40 - 58 486 $1.25 / $10 400K 1267.986 [1236.1, 1299.9] 264.38 · 不稳 Proprietary
11
gpt-5-chat OpenAI · Proprietary
1253±25.4 51 - 80 1.4K $1.25 / $10 128K 1252.783 [1227.4, 1278.1] 167.42 · 不稳 Proprietary
12
grok-4-0709 xAI · Proprietary
1249±25.7 71 - 100 1.2K $3 / $15 256K 1248.651 [1222.9, 1274.4] 172.49 · 不稳 Proprietary
13
chatgpt-4o-latest-20250326 OpenAI · Proprietary
1241±25.7 33 - 53 1.1K $5 / $15 128K 1240.782 [1215.1, 1266.4] 171.39 · 不稳 Proprietary
14
gpt-5-high OpenAI · Proprietary
1232±25.1 45 - 65 1.5K $1.25 / $10 400K 1231.981 [1206.9, 1257.1] 164.03 · 不稳 Proprietary
15
o3-2025-04-16 OpenAI · Proprietary
1224±24.3 48 - 69 1.7K $2 / $8 200K 1224.178 [1199.9, 1248.5] 153.73 · 不稳 Proprietary
16
gpt-4.1-2025-04-14 OpenAI · Proprietary
1224±23.9 69 - 93 1.4K $2 / $8 1M 1223.599 [1199.7, 1247.5] 149.31 · 不稳 Proprietary
17
o1-2024-12-17 OpenAI · Proprietary
1223±57.9 88 - 110 99 $15 / $60 200K 1222.558 [1164.7, 1280.5] 872.48 · 不稳 Proprietary
18
gemini-2.5-flash-lite-preview-09-2025-no-thinking Google · Proprietary
1221±31.6 116 - 132 446 $0.10 / $0.40 1M 1220.580 [1189.0, 1252.2] 260.36 · 不稳 Proprietary
19
gpt-5-mini-high OpenAI · Proprietary
1213±27.0 101 - 126 1.0K $0.25 / $2 400K 1213.099 [1186.1, 1240.1] 189.17 · 不稳 Proprietary
20
o4-mini-2025-04-16 OpenAI · Proprietary
1201±25.4 102 - 126 1.3K $1.10 / $4.40 200K 1201.018 [1175.6, 1226.4] 168.19 · 不稳 Proprietary
21
gemini-2.5-flash-lite-preview-06-17-thinking Google · Proprietary
1188±27.0 122 - 137 1.0K $0.10 / $0.40 1M 1188.000 [1161.0, 1215.0] 189.13 · 不稳 Proprietary
22
gpt-4.1-mini-2025-04-14 OpenAI · Proprietary
1182±25.0 111 - 131 1.2K $0.40 / $1.60 1M 1181.758 [1156.7, 1206.8] 163.14 · 不稳 Proprietary
23
mistral-medium-2508 Mistral · Proprietary
1177±25.8 74 - 98 1.3K $2.70 / $8.10 32K 1176.689 [1150.9, 1202.5] 173.01 · 不稳 Proprietary
24
gemini-1.5-pro-002 Google · Proprietary
1174±37.2 143 - 169 395 $3.50 / $10.50 2.1M 1173.936 [1136.8, 1211.1] 359.80 · 不稳 Proprietary
25
gpt-4.5-preview-2025-02-27 OpenAI · Proprietary
1162±63.0 29 - 55 77 $75 / $150 128K 1161.802 [1098.8, 1224.8] 1034.02 · 不稳 Proprietary
26
gemma-3-27b-it Google · Gemma
1155±28.4 131 - 147 776 $0.08 / $0.16 131.1K 1154.710 [1126.3, 1183.1] 209.75 · 不稳 Gemma
27
claude-3-7-sonnet-20250219 Anthropic · Proprietary
1137±49.2 127 - 142 157 $3 / $15 200K 1137.261 [1088.1, 1186.4] 629.22 · 不稳 Proprietary
28
mistral-medium-2505 Mistral · Proprietary
1133±32.0 105 - 127 497 $0.40 / $2 131.1K 1133.059 [1101.1, 1165.0] 265.80 · 不稳 Proprietary
29
gemini-2.0-flash-001 Google · Proprietary
1132±34.7 135 - 156 330 $0.10 / $0.40 1M 1131.615 [1096.9, 1166.3] 313.58 · 不稳 Proprietary
30
mistral-small-2506 Mistral · Apache 2.0
1131±32.8 137 - 163 497 $0.10 / $0.30 32K 1131.289 [1098.5, 1164.1] 280.24 · 不稳 Apache 2.0
31
mistral-small-3.1-24b-instruct-2503 Mistral · Apache 2.0
1131±29.4 207 - 221 753 $0.10 / $0.30 32K 1130.637 [1101.2, 1160.0] 224.92 · 不稳 Apache 2.0
32
gemini-1.5-flash-002 Google · Proprietary
1124±38.0 196 - 220 370 $0.07 / $0.30 1M 1124.372 [1086.3, 1162.4] 376.56 · 不稳 Proprietary
33
gpt-4o-2024-05-13 OpenAI · Proprietary
1119±30.3 150 - 173 1.5K $5 / $15 128K 1119.297 [1089.0, 1149.6] 238.68 · 不稳 Proprietary
34
llama-4-maverick-17b-128e-instruct Meta · Llama 4
1117±39.0 173 - 200 248 $0.63 / $1.80 131.1K 1116.524 [1077.5, 1155.5] 396.01 · 不稳 Llama 4
35
claude-3-5-sonnet-20241022 Anthropic · Proprietary
1107±31.7 127 - 138 518 $3 / $15 200K 1107.133 [1075.4, 1138.8] 261.83 · 不稳 Proprietary
36
qwen2.5-vl-72b-instruct 阿里巴巴 · Qwen
1094±53.3 119 1093.529 [1040.2, 1146.9] 740.77 · 不稳 Qwen
37
claude-3-5-sonnet-20240620 Anthropic · Proprietary
1092±31.4 152 - 179 1.6K $3 / $15 200K 1092.304 [1060.9, 1123.7] 256.28 · 不稳 Proprietary
38
pixtral-large-2411 Mistral · MRL
1070±47.4 156 1070.003 [1022.6, 1117.4] 584.28 · 不稳 MRL
39
llama-4-scout-17b-16e-instruct Meta · Llama
1068±40.4 179 - 206 249 $0.40 / $0.70 8.2K 1067.995 [1027.6, 1108.4] 424.76 · 不稳 Llama
40
qwen2-vl-72b 阿里巴巴 · Qwen
1059±39.3 291 1058.971 [1019.7, 1098.2] 401.50 · 不稳 Qwen
41
internvl2-26b OpenGVLab · MIT
1052±42.5 287 1051.964 [1009.5, 1094.5] 469.99 · 不稳 MIT
42
gpt-4-turbo-2024-04-09 OpenAI · Proprietary
1032±33.3 179 - 205 937 $10 / $30 128K 1032.071 [998.8, 1065.4] 288.57 · 不稳 Proprietary
43
gpt-4o-mini-2024-07-18 OpenAI · Proprietary
1020±30.5 184 - 209 952 $0.15 / $0.60 128K 1019.840 [989.4, 1050.3] 241.62 · 不稳 Proprietary
44
gemini-1.5-pro-001 Google · Proprietary
1017±32.7 179 - 205 1.2K $3.50 / $10.50 2.1M 1017.405 [984.7, 1050.2] 279.19 · 不稳 Proprietary
45
gemini-2.0-flash-lite-preview-02-05 Google · Proprietary
1012±60.1 141 - 168 98 $0.07 / $0.30 1M 1012.041 [951.9, 1072.2] 941.31 · 不稳 Proprietary
46
gpt-4o-2024-08-06 OpenAI · Proprietary
997±47.1 157 - 187 186 $2.50 / $10 128K 996.826 [949.8, 1043.9] 576.53 · 不稳 Proprietary
47
qwen2-vl-7b-instruct 阿里巴巴 · Apache 2.0
987±39.9 298 986.583 [946.7, 1026.5] 414.85 · 不稳 Apache 2.0
48
claude-3-opus-20240229 Anthropic · Proprietary
981±33.0 181 - 206 1.0K $15 / $75 200K 981.198 [948.2, 1014.2] 284.19 · 不稳 Proprietary
49
gemini-1.5-flash-8b-001 Google · Proprietary
961±38.4 242 - 253 332 $0.07 / $0.30 1M 960.914 [922.5, 999.4] 384.85 · 不稳 Proprietary
50
gemini-1.5-flash-001 Google · Proprietary
947±33.6 221 - 236 950 $0.07 / $0.30 1M 946.818 [913.2, 980.4] 293.46 · 不稳 Proprietary
51
llama-3.2-vision-90b-instruct Meta · Llama 3.2
940±36.9 393 939.591 [902.7, 976.5] 353.85 · 不稳 Llama 3.2
52
pixtral-12b-2409 Mistral · Apache 2.0
938±38.4 335 937.893 [899.5, 976.3] 384.43 · 不稳 Apache 2.0
53
internvl2-4b OpenGVLab · MIT
937±50.0 177 937.459 [887.4, 987.5] 651.21 · 不稳 MIT
54
claude-3-sonnet-20240229 Anthropic · Proprietary
929±33.7 225 - 242 915 $3 / $15 200K 929.396 [895.7, 963.1] 295.30 · 不稳 Proprietary
55
molmo-72b-0924 Allen AI · Apache 2.0
924±50.1 182 923.781 [873.7, 973.9] 653.36 · 不稳 Apache 2.0
56
claude-3-haiku-20240307 Anthropic · Proprietary
903±33.7 242 - 252 1.0K $0.25 / $1.25 200K 902.670 [869.0, 936.3] 294.92 · 不稳 Proprietary
57
llama-3.2-vision-11b-instruct Meta · Llama 3.2
902±43.1 266 902.102 [859.0, 945.2] 484.12 · 不稳 Llama 3.2
58
llava-v1.6-34b LLaVA · Apache 2.0
902±40.2 415 901.882 [861.7, 942.1] 420.78 · 不稳 Apache 2.0
59
molmo-7b-d-0924 Allen AI · Apache 2.0
877±49.0 171 877.474 [828.5, 926.5] 625.29 · 不稳 Apache 2.0

没有找到相关模型