排名 模型 得分
🥇
gemini-3.1-pro-preview Google · Proprietary
1378±34.5 1 - 7 403 $2 / $12 1M 1378.101 [1343.6, 1412.6] 308.99 · 不稳 Proprietary
🥈
dola-seed-2.0-preview 字节跳动 · Proprietary
1374±50.7 161 1374.448 [1323.7, 1425.2] 669.51 · 不稳 Proprietary
🥉
gemini-3-pro Google · Proprietary
1374±23.9 4 - 10 1.4K $2 / $12 1M 1373.631 [1349.8, 1397.5] 148.16 · 不稳 Proprietary
4
kimi-k2.5-instant 月之暗面 · Modified MIT
1348±46.7 44 - 74 170 $0.44 / $2 262.1K 1348.358 [1301.7, 1395.0] 567.00 · 不稳 Modified MIT
5
gemini-3-flash Google · Proprietary
1336±29.5 8 - 21 653 $0.50 / $3 1M 1335.871 [1306.3, 1365.4] 227.30 · 不稳 Proprietary
6
kimi-k2.5-thinking 月之暗面 · Modified MIT
1333±35.4 25 - 47 353 $0.60 / $3 Unknown 1332.681 [1297.3, 1368.0] 325.58 · 不稳 Modified MIT
7
gpt-5.2-high OpenAI · Proprietary
1328±37.2 37 - 57 309 $1.75 / $14 400K 1328.277 [1291.1, 1365.5] 360.31 · 不稳 Proprietary
8
qwen3.5-397b-a17b 阿里巴巴 · Apache 2.0
1319±49.6 28 - 52 156 $0.39 / $2.34 262.1K 1318.551 [1268.9, 1368.2] 640.45 · 不稳 Apache 2.0
9
gemini-3-flash (thinking-minimal) Google · Proprietary
1302±30.9 15 - 29 529 $0.50 / $3 1M 1302.374 [1271.4, 1333.3] 249.17 · 不稳 Proprietary
10
qwen3.5-122b-a10b 阿里巴巴 · Apache 2.0
1301±56.7 60 - 88 111 $0.26 / $2.08 262.1K 1300.632 [1243.9, 1357.3] 837.38 · 不稳 Apache 2.0
11
gemini-2.5-flash-preview-09-2025 Google · Proprietary
1294±32.0 81 - 107 400 $0.30 / $2.50 1M 1293.753 [1261.8, 1325.7] 265.82 · 不稳 Proprietary
12
qwen3-vl-235b-a22b-instruct 阿里巴巴 · Apache 2.0
1288±26.9 61 - 93 741 $0.20 / $0.88 262.1K 1287.615 [1260.7, 1314.6] 188.90 · 不稳 Apache 2.0
13
gemini-2.5-pro Google · Proprietary
1285±21.5 29 - 47 2.5K $1.25 / $10 1M 1284.596 [1263.1, 1306.1] 120.77 · 不稳 Proprietary
14
gemini-2.5-flash Google · Proprietary
1284±22.1 71 - 96 2.0K $0.30 / $2.50 1M 1283.593 [1261.5, 1305.7] 126.87 · 不稳 Proprietary
15
gemini-3.1-flash-lite-preview Google · Proprietary
1283±40.7 37 - 59 253 $0.25 / $1.50 1M 1283.460 [1242.7, 1324.2] 431.94 · 不稳 Proprietary
16
gpt-5.2 OpenAI · Proprietary
1279±36.1 40 - 59 346 $1.75 / $14 400K 1279.427 [1243.4, 1315.5] 338.53 · 不稳 Proprietary
17
gpt-5.1-high OpenAI · Proprietary
1278±31.9 21 - 40 463 $1.25 / $10 400K 1277.806 [1245.9, 1309.7] 264.82 · 不稳 Proprietary
18
gpt-5.2-chat-latest-20260210 OpenAI · Proprietary
1270±51.4 8 - 20 148 $1.75 / $14 128K 1269.997 [1218.6, 1321.4] 688.57 · 不稳 Proprietary
19
ernie-5.0-preview-1220 百度 · Proprietary
1268±47.1 176 1268.023 [1221.0, 1315.1] 576.42 · 不稳 Proprietary
20
gpt-5.1 OpenAI · Proprietary
1256±29.1 40 - 58 571 $1.25 / $10 400K 1255.603 [1226.5, 1284.7] 221.07 · 不稳 Proprietary
21
gpt-5-chat OpenAI · Proprietary
1255±23.8 51 - 80 1.3K $1.25 / $10 128K 1255.449 [1231.7, 1279.2] 146.97 · 不稳 Proprietary
22
grok-4-1-fast-reasoning xAI · Proprietary
1255±54.8 47 - 67 127 $0.20 / $0.50 2M 1254.968 [1200.2, 1309.8] 781.32 · 不稳 Proprietary
23
grok-4-0709 xAI · Proprietary
1253±24.2 71 - 100 1.2K $3 / $15 256K 1253.179 [1228.9, 1277.4] 152.91 · 不稳 Proprietary
24
chatgpt-4o-latest-20250326 OpenAI · Proprietary
1247±24.0 33 - 53 1.1K $5 / $15 128K 1246.521 [1222.5, 1270.5] 149.61 · 不稳 Proprietary
25
gpt-5-high OpenAI · Proprietary
1234±23.5 45 - 65 1.4K $1.25 / $10 400K 1233.719 [1210.2, 1257.3] 144.24 · 不稳 Proprietary
26
o3-2025-04-16 OpenAI · Proprietary
1230±22.6 48 - 69 1.6K $2 / $8 200K 1229.570 [1207.0, 1252.2] 132.95 · 不稳 Proprietary
27
o1-2024-12-17 OpenAI · Proprietary
1226±57.8 88 - 110 99 $15 / $60 200K 1226.387 [1168.5, 1284.2] 871.03 · 不稳 Proprietary
28
gemini-2.5-flash-lite-preview-09-2025-no-thinking Google · Proprietary
1226±30.5 116 - 132 419 $0.10 / $0.40 1M 1226.127 [1195.6, 1256.6] 242.05 · 不稳 Proprietary
29
gpt-4.1-2025-04-14 OpenAI · Proprietary
1226±22.4 69 - 93 1.4K $2 / $8 1M 1225.773 [1203.4, 1248.1] 130.08 · 不稳 Proprietary
30
gpt-5-mini-high OpenAI · Proprietary
1213±25.3 101 - 126 1.0K $0.25 / $2 400K 1213.281 [1187.9, 1238.6] 167.05 · 不稳 Proprietary
31
o4-mini-2025-04-16 OpenAI · Proprietary
1203±23.6 102 - 126 1.3K $1.10 / $4.40 200K 1202.919 [1179.3, 1226.6] 145.39 · 不稳 Proprietary
32
gemini-2.5-flash-lite-preview-06-17-thinking Google · Proprietary
1188±25.4 122 - 137 1.0K $0.10 / $0.40 1M 1188.000 [1162.6, 1213.4] 168.24 · 不稳 Proprietary
33
gpt-4.1-mini-2025-04-14 OpenAI · Proprietary
1184±23.5 111 - 131 1.2K $0.40 / $1.60 1M 1184.267 [1160.7, 1207.8] 144.32 · 不稳 Proprietary
34
gemini-1.5-pro-002 Google · Proprietary
1178±39.0 143 - 169 395 $3.50 / $10.50 2.1M 1177.855 [1138.9, 1216.8] 395.83 · 不稳 Proprietary
35
mistral-medium-2508 Mistral · Proprietary
1177±23.5 74 - 98 1.4K $2.70 / $8.10 32K 1177.152 [1153.6, 1200.7] 144.04 · 不稳 Proprietary
36
gpt-4.5-preview-2025-02-27 OpenAI · Proprietary
1166±63.0 29 - 55 77 $75 / $150 128K 1165.901 [1102.9, 1228.9] 1033.07 · 不稳 Proprietary
37
gemma-3-27b-it Google · Gemma
1152±27.1 131 - 147 756 $0.08 / $0.16 131.1K 1152.071 [1124.9, 1179.2] 191.88 · 不稳 Gemma
38
claude-3-7-sonnet-20250219 Anthropic · Proprietary
1145±49.1 127 - 142 154 $3 / $15 200K 1144.745 [1095.6, 1193.9] 627.87 · 不稳 Proprietary
39
mistral-medium-2505 Mistral · Proprietary
1139±30.9 105 - 127 488 $0.40 / $2 131.1K 1139.112 [1108.2, 1170.0] 248.63 · 不稳 Proprietary
40
mistral-small-2506 Mistral · Apache 2.0
1138±31.6 137 - 163 493 $0.10 / $0.30 32K 1138.290 [1106.7, 1169.8] 259.17 · 不稳 Apache 2.0
41
mistral-small-3.1-24b-instruct-2503 Mistral · Apache 2.0
1135±28.1 207 - 221 740 $0.10 / $0.30 32K 1135.417 [1107.3, 1163.5] 205.84 · 不稳 Apache 2.0
42
gemini-2.0-flash-001 Google · Proprietary
1135±33.1 135 - 156 343 $0.10 / $0.40 1M 1135.361 [1102.2, 1168.5] 285.86 · 不稳 Proprietary
43
gemini-1.5-flash-002 Google · Proprietary
1128±39.8 196 - 220 370 $0.07 / $0.30 1M 1128.288 [1088.5, 1168.1] 412.80 · 不稳 Proprietary
44
gpt-4o-2024-05-13 OpenAI · Proprietary
1123±32.7 150 - 173 1.5K $5 / $15 128K 1123.215 [1090.5, 1155.9] 277.88 · 不稳 Proprietary
45
llama-4-maverick-17b-128e-instruct Meta · Llama 4
1120±39.2 173 - 200 239 $0.63 / $1.80 131.1K 1120.322 [1081.1, 1159.5] 399.75 · 不稳 Llama 4
46
claude-3-5-sonnet-20241022 Anthropic · Proprietary
1111±33.7 127 - 138 514 $3 / $15 200K 1110.999 [1077.3, 1144.7] 296.19 · 不稳 Proprietary
47
qwen2.5-vl-72b-instruct 阿里巴巴 · Qwen
1098±53.7 119 1097.536 [1043.8, 1151.2] 750.56 · 不稳 Qwen
48
claude-3-5-sonnet-20240620 Anthropic · Proprietary
1096±33.7 152 - 179 1.6K $3 / $15 200K 1096.223 [1062.5, 1130.0] 296.29 · 不稳 Proprietary
49
pixtral-large-2411 Mistral · MRL
1074±48.3 156 1073.904 [1025.6, 1122.2] 606.76 · 不稳 MRL
50
llama-4-scout-17b-16e-instruct Meta · Llama
1070±40.3 179 - 206 242 $0.40 / $0.70 8.2K 1069.799 [1029.5, 1110.1] 423.23 · 不稳 Llama
51
qwen2-vl-72b 阿里巴巴 · Qwen
1063±41.1 291 1062.884 [1021.8, 1103.9] 438.80 · 不稳 Qwen
52
internvl2-26b OpenGVLab · MIT
1056±44.3 287 1055.884 [1011.6, 1100.2] 510.34 · 不稳 MIT
53
gpt-4-turbo-2024-04-09 OpenAI · Proprietary
1036±35.5 179 - 205 937 $10 / $30 128K 1035.991 [1000.5, 1071.5] 328.79 · 不稳 Proprietary
54
gpt-4o-mini-2024-07-18 OpenAI · Proprietary
1024±32.7 184 - 209 952 $0.15 / $0.60 128K 1023.765 [991.0, 1056.5] 278.67 · 不稳 Proprietary
55
gemini-1.5-pro-001 Google · Proprietary
1021±35.0 179 - 205 1.2K $3.50 / $10.50 2.1M 1021.325 [986.3, 1056.4] 319.37 · 不稳 Proprietary
56
gemini-2.0-flash-lite-preview-02-05 Google · Proprietary
1016±60.6 141 - 168 98 $0.07 / $0.30 1M 1016.083 [955.5, 1076.6] 954.85 · 不稳 Proprietary
57
gpt-4o-2024-08-06 OpenAI · Proprietary
1001±48.6 157 - 187 186 $2.50 / $10 128K 1000.733 [952.2, 1049.3] 614.07 · 不稳 Proprietary
58
qwen2-vl-7b-instruct 阿里巴巴 · Apache 2.0
990±41.7 298 990.497 [948.8, 1032.2] 452.45 · 不稳 Apache 2.0
59
claude-3-opus-20240229 Anthropic · Proprietary
985±35.3 181 - 206 1.0K $15 / $75 200K 985.118 [949.8, 1020.4] 324.31 · 不稳 Proprietary
60
gemini-1.5-flash-8b-001 Google · Proprietary
965±40.3 242 - 253 332 $0.07 / $0.30 1M 964.827 [924.6, 1005.1] 422.08 · 不稳 Proprietary
61
gemini-1.5-flash-001 Google · Proprietary
951±35.8 221 - 236 950 $0.07 / $0.30 1M 950.738 [914.9, 986.5] 333.71 · 不稳 Proprietary
62
llama-3.2-vision-90b-instruct Meta · Llama 3.2
944±38.7 393 943.508 [904.8, 982.2] 390.21 · 不稳 Llama 3.2
63
pixtral-12b-2409 Mistral · Apache 2.0
942±40.2 335 941.808 [901.7, 982.0] 419.69 · 不稳 Apache 2.0
64
internvl2-4b OpenGVLab · MIT
941±51.6 177 941.377 [889.8, 992.9] 691.81 · 不稳 MIT
65
claude-3-sonnet-20240229 Anthropic · Proprietary
933±35.9 225 - 242 915 $3 / $15 200K 933.316 [897.4, 969.2] 335.56 · 不稳 Proprietary
66
molmo-72b-0924 Allen AI · Apache 2.0
928±51.6 182 927.689 [876.1, 979.2] 691.92 · 不稳 Apache 2.0
67
claude-3-haiku-20240307 Anthropic · Proprietary
907±35.9 242 - 252 1.0K $0.25 / $1.25 200K 906.590 [870.7, 942.5] 335.25 · 不稳 Proprietary
68
llama-3.2-vision-11b-instruct Meta · Llama 3.2
906±44.8 266 906.015 [861.2, 950.8] 522.54 · 不稳 Llama 3.2
69
llava-v1.6-34b LLaVA · Apache 2.0
906±42.1 415 905.801 [863.7, 947.9] 461.64 · 不稳 Apache 2.0
70
molmo-7b-d-0924 Allen AI · Apache 2.0
881±50.5 171 881.380 [830.9, 931.9] 663.28 · 不稳 Apache 2.0

没有找到相关模型