排名 模型 得分
🥇
gemini-3-pro Google · Proprietary
1391±22.2 4 - 10 766 $2 / $12 1M 1390.639 [1368.4, 1412.8] 128.23 · 不稳 Proprietary
🥈
ernie-5.0-preview-1220 百度 · Proprietary
1336±45.1 176 1336.076 [1291.0, 1381.1] 528.34 · 不稳 Proprietary
🥉
gemini-3-flash Google · Proprietary
1306±39.8 8 - 21 217 $0.50 / $3 1M 1306.364 [1266.6, 1346.1] 411.42 · 不稳 Proprietary
4
gpt-5.1 OpenAI · Proprietary
1291±29.6 40 - 58 411 $1.25 / $10 400K 1291.264 [1261.7, 1320.9] 228.17 · 不稳 Proprietary
5
gemini-2.5-flash-preview-09-2025 Google · Proprietary
1289±24.7 81 - 107 555 $0.30 / $2.50 1M 1288.640 [1263.9, 1313.3] 158.74 · 不稳 Proprietary
6
gpt-5.1-high OpenAI · Proprietary
1282±30.2 21 - 40 385 $1.25 / $10 400K 1282.408 [1252.2, 1312.7] 238.12 · 不稳 Proprietary
7
gemini-2.5-pro Google · Proprietary
1277±13.8 29 - 47 2.4K $1.25 / $10 1M 1277.362 [1263.5, 1291.2] 49.81 · 不稳 Proprietary
8
grok-4-0709 xAI · Proprietary
1265±16.2 71 - 100 1.5K $3 / $15 256K 1265.341 [1249.1, 1281.6] 68.69 · 不稳 Proprietary
9
claude-opus-4-20250514 Anthropic · Proprietary
1253±32.7 70 - 96 192 $15 / $75 200K 1253.428 [1220.8, 1286.1] 277.63 · 不稳 Proprietary
10
gemini-2.5-flash Google · Proprietary
1253±14.8 71 - 96 1.7K $0.30 / $2.50 1M 1253.055 [1238.3, 1267.8] 56.91 · 不稳 Proprietary
11
chatgpt-4o-latest-20250326 OpenAI · Proprietary
1248±18.1 33 - 53 1.0K $5 / $15 128K 1247.843 [1229.7, 1266.0] 85.56 · 不稳 Proprietary
12
gpt-5-chat OpenAI · Proprietary
1239±15.7 51 - 80 1.5K $1.25 / $10 128K 1239.480 [1223.7, 1255.2] 64.43 · 不稳 Proprietary
13
qwen3-vl-235b-a22b-thinking 阿里巴巴 · Apache 2.0
1230±38.2 91 - 123 219 $0.26 / $2.60 131.1K 1229.905 [1191.7, 1268.1] 379.67 · 不稳 Apache 2.0
14
qwen3-vl-235b-a22b-instruct 阿里巴巴 · Apache 2.0
1225±21.9 61 - 93 690 $0.20 / $0.88 262.1K 1224.788 [1202.8, 1246.7] 125.31 · 不稳 Apache 2.0
15
mistral-medium-2508 Mistral · Proprietary
1223±16.4 74 - 98 1.4K $2.70 / $8.10 32K 1223.059 [1206.6, 1239.5] 70.16 · 不稳 Proprietary
16
gpt-4.1-2025-04-14 OpenAI · Proprietary
1223±16.3 69 - 93 1.4K $2 / $8 1M 1222.903 [1206.6, 1239.2] 68.79 · 不稳 Proprietary
17
gemini-2.5-flash-lite-preview-09-2025-no-thinking Google · Proprietary
1220±24.3 116 - 132 565 $0.10 / $0.40 1M 1220.098 [1195.8, 1244.4] 153.28 · 不稳 Proprietary
18
gemini-2.0-flash-001 Google · Proprietary
1205±33.2 135 - 156 292 $0.10 / $0.40 1M 1205.259 [1172.0, 1238.5] 287.79 · 不稳 Proprietary
19
o3-2025-04-16 OpenAI · Proprietary
1197±14.1 48 - 69 1.9K $2 / $8 200K 1197.189 [1183.1, 1211.3] 51.92 · 不稳 Proprietary
20
claude-sonnet-4-20250514 Anthropic · Proprietary
1191±39.5 102 - 126 156 $3 / $15 1M 1191.332 [1151.8, 1230.8] 405.99 · 不稳 Proprietary
21
gpt-5-high OpenAI · Proprietary
1189±15.4 45 - 65 1.6K $1.25 / $10 400K 1188.830 [1173.4, 1204.3] 61.94 · 不稳 Proprietary
22
gemini-2.5-flash-lite-preview-06-17-thinking Google · Proprietary
1188±17.2 122 - 137 1.3K $0.10 / $0.40 1M 1188.350 [1171.2, 1205.5] 76.68 · 不稳 Proprietary
23
mistral-small-2506 Mistral · Apache 2.0
1185±28.0 137 - 163 442 $0.10 / $0.30 32K 1185.307 [1157.3, 1213.3] 204.39 · 不稳 Apache 2.0
24
qwen-vl-max-2025-08-13 阿里巴巴 · Proprietary
1183±42.3 191 1183.447 [1141.2, 1225.7] 465.50 · 不稳 Proprietary
25
gemma-3-27b-it Google · Gemma
1182±21.5 131 - 147 732 $0.08 / $0.16 131.1K 1182.131 [1160.7, 1203.6] 120.11 · 不稳 Gemma
26
gpt-5-mini-high OpenAI · Proprietary
1181±18.2 101 - 126 1.1K $0.25 / $2 400K 1181.311 [1163.1, 1199.5] 85.92 · 不稳 Proprietary
27
hunyuan-vision-1.5-thinking 腾讯 · Proprietary
1176±35.9 81 - 126 275 Free / N/A Unknown 1175.706 [1139.8, 1211.6] 334.72 · 不稳 Proprietary
28
mistral-medium-2505 Mistral · Proprietary
1169±24.6 105 - 127 518 $0.40 / $2 131.1K 1168.636 [1144.0, 1193.3] 157.93 · 不稳 Proprietary
29
gpt-4.1-mini-2025-04-14 OpenAI · Proprietary
1165±17.5 111 - 131 1.3K $0.40 / $1.60 1M 1164.890 [1147.4, 1182.4] 79.61 · 不稳 Proprietary
30
o4-mini-2025-04-16 OpenAI · Proprietary
1161±16.1 102 - 126 1.4K $1.10 / $4.40 200K 1161.101 [1145.0, 1177.2] 67.68 · 不稳 Proprietary
31
mistral-small-3.1-24b-instruct-2503 Mistral · Apache 2.0
1143±21.6 207 - 221 777 $0.10 / $0.30 32K 1143.494 [1121.9, 1165.1] 121.38 · 不稳 Apache 2.0
32
llama-4-scout-17b-16e-instruct Meta · Llama
1127±36.6 179 - 206 265 $0.40 / $0.70 8.2K 1126.760 [1090.1, 1163.4] 349.03 · 不稳 Llama
33
gpt-5-nano-high OpenAI · Proprietary
1117±40.4 154 - 187 206 $0.05 / $0.40 400K 1117.232 [1076.8, 1157.6] 424.86 · 不稳 Proprietary
34
llama-4-maverick-17b-128e-instruct Meta · Llama 4
1113±38.0 173 - 200 250 $0.63 / $1.80 131.1K 1112.913 [1074.9, 1150.9] 375.21 · 不稳 Llama 4

没有找到相关模型