排名 模型 得分
🥇
gemini-3.1-pro-preview Google · Proprietary
1384±45.2 1 - 7 179 $2 / $12 1M 1384.072 [1338.8, 1429.3] 532.89 · 不稳 Proprietary
🥈
gemini-3-pro Google · Proprietary
1366±25.8 4 - 10 1.3K $2 / $12 1M 1365.924 [1340.1, 1391.8] 173.91 · 不稳 Proprietary
🥉
kimi-k2.5-instant 月之暗面 · Modified MIT
1345±50.0 44 - 74 157 $0.44 / $2 262.1K 1345.330 [1295.4, 1395.3] 650.09 · 不稳 Modified MIT
4
kimi-k2.5-thinking 月之暗面 · Modified MIT
1334±42.6 25 - 47 226 $0.60 / $3 Unknown 1333.760 [1291.1, 1376.4] 473.04 · 不稳 Modified MIT
5
gpt-5.2-high OpenAI · Proprietary
1332±44.2 37 - 57 195 $1.75 / $14 400K 1331.906 [1287.7, 1376.1] 507.77 · 不稳 Proprietary
6
gemini-3-flash Google · Proprietary
1326±32.3 8 - 21 563 $0.50 / $3 1M 1326.184 [1293.8, 1358.5] 272.17 · 不稳 Proprietary
7
gemini-2.5-flash-preview-09-2025 Google · Proprietary
1298±34.5 81 - 107 345 $0.30 / $2.50 1M 1297.603 [1263.1, 1332.1] 310.01 · 不稳 Proprietary
8
qwen3-vl-235b-a22b-instruct 阿里巴巴 · Apache 2.0
1295±28.7 61 - 93 682 $0.20 / $0.88 262.1K 1294.507 [1265.8, 1323.3] 215.15 · 不稳 Apache 2.0
9
gemini-3-flash (thinking-minimal) Google · Proprietary
1292±34.1 15 - 29 445 $0.50 / $3 1M 1292.373 [1258.2, 1326.5] 303.25 · 不稳 Proprietary
10
gemini-2.5-pro Google · Proprietary
1283±23.7 29 - 47 2.3K $1.25 / $10 1M 1282.905 [1259.2, 1306.6] 145.72 · 不稳 Proprietary
11
gemini-2.5-flash Google · Proprietary
1278±24.2 71 - 96 1.7K $0.30 / $2.50 1M 1278.325 [1254.1, 1302.6] 152.91 · 不稳 Proprietary
12
gpt-5.1-high OpenAI · Proprietary
1276±34.0 21 - 40 429 $1.25 / $10 400K 1276.355 [1242.4, 1310.4] 300.86 · 不稳 Proprietary
13
ernie-5.0-preview-1220 百度 · Proprietary
1276±48.4 175 1275.836 [1227.5, 1324.2] 609.14 · 不稳 Proprietary
14
gpt-5.2 OpenAI · Proprietary
1272±42.7 40 - 59 225 $1.75 / $14 400K 1271.699 [1229.0, 1314.4] 474.88 · 不稳 Proprietary
15
gpt-5.1 OpenAI · Proprietary
1256±30.9 40 - 58 537 $1.25 / $10 400K 1256.208 [1225.3, 1287.1] 249.12 · 不稳 Proprietary
16
grok-4-0709 xAI · Proprietary
1247±26.3 71 - 100 1.1K $3 / $15 256K 1246.988 [1220.6, 1273.3] 180.62 · 不稳 Proprietary
17
gpt-5-chat OpenAI · Proprietary
1247±26.0 51 - 80 1.2K $1.25 / $10 128K 1246.935 [1220.9, 1272.9] 175.84 · 不稳 Proprietary
18
chatgpt-4o-latest-20250326 OpenAI · Proprietary
1243±25.6 33 - 53 1.1K $5 / $15 128K 1243.460 [1217.8, 1269.1] 170.81 · 不稳 Proprietary
19
gpt-5-high OpenAI · Proprietary
1231±25.7 45 - 65 1.2K $1.25 / $10 400K 1230.596 [1204.9, 1256.3] 171.96 · 不稳 Proprietary
20
o3-2025-04-16 OpenAI · Proprietary
1225±24.6 48 - 69 1.5K $2 / $8 200K 1225.062 [1200.5, 1249.6] 157.27 · 不稳 Proprietary
21
gpt-4.1-2025-04-14 OpenAI · Proprietary
1224±24.3 69 - 93 1.3K $2 / $8 1M 1224.394 [1200.1, 1248.7] 153.34 · 不稳 Proprietary
22
o1-2024-12-17 OpenAI · Proprietary
1223±57.9 88 - 110 99 $15 / $60 200K 1222.648 [1164.8, 1280.5] 872.01 · 不稳 Proprietary
23
gemini-2.5-flash-lite-preview-09-2025-no-thinking Google · Proprietary
1219±33.7 116 - 132 346 $0.10 / $0.40 1M 1218.580 [1184.9, 1252.2] 295.02 · 不稳 Proprietary
24
gpt-5-mini-high OpenAI · Proprietary
1212±27.9 101 - 126 901 $0.25 / $2 400K 1212.336 [1184.4, 1240.2] 202.56 · 不稳 Proprietary
25
o4-mini-2025-04-16 OpenAI · Proprietary
1203±25.7 102 - 126 1.2K $1.10 / $4.40 200K 1203.484 [1177.8, 1229.2] 172.03 · 不稳 Proprietary
26
gemini-2.5-flash-lite-preview-06-17-thinking Google · Proprietary
1188±27.6 122 - 137 935 $0.10 / $0.40 1M 1188.000 [1160.4, 1215.6] 198.47 · 不稳 Proprietary
27
gpt-4.1-mini-2025-04-14 OpenAI · Proprietary
1188±25.4 111 - 131 1.1K $0.40 / $1.60 1M 1187.564 [1162.1, 1213.0] 168.29 · 不稳 Proprietary
28
mistral-medium-2508 Mistral · Proprietary
1177±25.8 74 - 98 1.3K $2.70 / $8.10 32K 1176.524 [1150.8, 1202.3] 172.66 · 不稳 Proprietary
29
gemini-1.5-pro-002 Google · Proprietary
1172±37.6 143 - 169 395 $3.50 / $10.50 2.1M 1172.440 [1134.8, 1210.1] 368.44 · 不稳 Proprietary
30
gpt-4.5-preview-2025-02-27 OpenAI · Proprietary
1162±63.2 29 - 55 77 $75 / $150 128K 1161.960 [1098.7, 1225.2] 1041.22 · 不稳 Proprietary
31
gemma-3-27b-it Google · Gemma
1158±30.0 131 - 147 634 $0.08 / $0.16 131.1K 1158.370 [1128.3, 1188.4] 234.59 · 不稳 Gemma
32
claude-3-7-sonnet-20250219 Anthropic · Proprietary
1140±49.5 127 - 142 155 $3 / $15 200K 1140.423 [1091.0, 1189.9] 636.77 · 不稳 Proprietary
33
mistral-medium-2505 Mistral · Proprietary
1136±32.4 105 - 127 471 $0.40 / $2 131.1K 1135.658 [1103.3, 1168.0] 272.50 · 不稳 Proprietary
34
mistral-small-3.1-24b-instruct-2503 Mistral · Apache 2.0
1133±29.6 207 - 221 716 $0.10 / $0.30 32K 1133.246 [1103.6, 1162.9] 228.54 · 不稳 Apache 2.0
35
mistral-small-2506 Mistral · Apache 2.0
1132±33.8 137 - 163 451 $0.10 / $0.30 32K 1132.416 [1098.6, 1166.2] 297.01 · 不稳 Apache 2.0
36
gemini-1.5-flash-002 Google · Proprietary
1123±38.5 196 - 220 370 $0.07 / $0.30 1M 1122.864 [1084.4, 1161.3] 385.39 · 不稳 Proprietary
37
gemini-2.0-flash-001 Google · Proprietary
1121±34.2 135 - 156 335 $0.10 / $0.40 1M 1121.155 [1086.9, 1155.4] 305.01 · 不稳 Proprietary
38
gpt-4o-2024-05-13 OpenAI · Proprietary
1118±30.9 150 - 173 1.5K $5 / $15 128K 1117.881 [1087.0, 1148.8] 248.07 · 不稳 Proprietary
39
llama-4-maverick-17b-128e-instruct Meta · Llama 4
1116±40.7 173 - 200 225 $0.63 / $1.80 131.1K 1115.896 [1075.2, 1156.6] 430.33 · 不稳 Llama 4
40
claude-3-5-sonnet-20241022 Anthropic · Proprietary
1105±32.3 127 - 138 516 $3 / $15 200K 1105.444 [1073.1, 1137.8] 272.21 · 不稳 Proprietary
41
qwen2.5-vl-72b-instruct 阿里巴巴 · Qwen
1093±53.4 119 1092.779 [1039.3, 1146.2] 743.53 · 不稳 Qwen
42
claude-3-5-sonnet-20240620 Anthropic · Proprietary
1091±32.0 152 - 179 1.6K $3 / $15 200K 1090.897 [1058.9, 1122.9] 265.85 · 不稳 Proprietary
43
llama-4-scout-17b-16e-instruct Meta · Llama
1076±42.1 179 - 206 225 $0.40 / $0.70 8.2K 1075.549 [1033.5, 1117.6] 460.80 · 不稳 Llama
44
pixtral-large-2411 Mistral · MRL
1069±47.7 156 1068.689 [1021.0, 1116.3] 591.19 · 不稳 MRL
45
qwen2-vl-72b 阿里巴巴 · Qwen
1057±39.7 291 1057.496 [1017.8, 1097.2] 410.43 · 不稳 Qwen
46
internvl2-26b OpenGVLab · MIT
1051±42.9 287 1050.570 [1007.6, 1093.5] 479.64 · 不稳 MIT
47
gpt-4-turbo-2024-04-09 OpenAI · Proprietary
1031±33.8 179 - 205 937 $10 / $30 128K 1030.686 [996.8, 1064.5] 298.19 · 不稳 Proprietary
48
gpt-4o-mini-2024-07-18 OpenAI · Proprietary
1019±31.0 184 - 209 952 $0.15 / $0.60 128K 1018.548 [987.5, 1049.6] 250.81 · 不稳 Proprietary
49
gemini-1.5-pro-001 Google · Proprietary
1016±33.3 179 - 205 1.2K $3.50 / $10.50 2.1M 1016.007 [982.7, 1049.3] 288.80 · 不稳 Proprietary
50
gemini-2.0-flash-lite-preview-02-05 Google · Proprietary
1012±60.2 141 - 168 98 $0.07 / $0.30 1M 1011.696 [951.5, 1071.9] 943.12 · 不稳 Proprietary
51
gpt-4o-2024-08-06 OpenAI · Proprietary
995±47.4 157 - 187 186 $2.50 / $10 128K 995.310 [947.9, 1042.7] 585.73 · 不稳 Proprietary
52
qwen2-vl-7b-instruct 阿里巴巴 · Apache 2.0
985±40.4 298 985.103 [944.8, 1025.5] 423.88 · 不稳 Apache 2.0
53
claude-3-opus-20240229 Anthropic · Proprietary
980±33.6 181 - 206 1.0K $15 / $75 200K 979.796 [946.2, 1013.4] 293.77 · 不稳 Proprietary
54
gemini-1.5-flash-8b-001 Google · Proprietary
959±38.9 242 - 253 332 $0.07 / $0.30 1M 959.375 [920.5, 998.2] 393.27 · 不稳 Proprietary
55
gemini-1.5-flash-001 Google · Proprietary
945±34.1 221 - 236 950 $0.07 / $0.30 1M 945.424 [911.3, 979.5] 303.09 · 不稳 Proprietary
56
llama-3.2-vision-90b-instruct Meta · Llama 3.2
938±37.3 393 938.099 [900.8, 975.4] 362.57 · 不稳 Llama 3.2
57
pixtral-12b-2409 Mistral · Apache 2.0
936±38.8 335 936.380 [897.5, 975.2] 392.60 · 不稳 Apache 2.0
58
internvl2-4b OpenGVLab · MIT
936±50.4 177 936.036 [885.6, 986.4] 660.89 · 不稳 MIT
59
claude-3-sonnet-20240229 Anthropic · Proprietary
928±34.2 225 - 242 915 $3 / $15 200K 928.005 [893.8, 962.2] 304.93 · 不稳 Proprietary
60
molmo-72b-0924 Allen AI · Apache 2.0
922±50.5 182 922.259 [871.8, 972.7] 662.64 · 不稳 Apache 2.0
61
claude-3-haiku-20240307 Anthropic · Proprietary
901±34.2 242 - 252 1.0K $0.25 / $1.25 200K 901.277 [867.1, 935.5] 304.56 · 不稳 Proprietary
62
llama-3.2-vision-11b-instruct Meta · Llama 3.2
901±43.5 266 900.625 [857.1, 944.2] 493.31 · 不稳 Llama 3.2
63
llava-v1.6-34b LLaVA · Apache 2.0
900±40.7 415 900.492 [859.8, 941.2] 430.50 · 不稳 Apache 2.0
64
molmo-7b-d-0924 Allen AI · Apache 2.0
876±49.4 171 875.945 [826.6, 925.3] 634.59 · 不稳 Apache 2.0

没有找到相关模型