排名 模型 得分
🥇
gemini-3-pro Google · Proprietary
1349±18.8 4 - 10 948 $2 / $12 1M 1349.026 [1330.3, 1367.8] 91.61 · 不稳 Proprietary
🥈
gemini-3-flash Google · Proprietary
1344±19.8 8 - 21 1.1K $0.50 / $3 1M 1344.406 [1324.6, 1364.2] 101.85 · 不稳 Proprietary
🥉
gemini-3-flash (thinking-minimal) Google · Proprietary
1308±24.1 15 - 29 595 $0.50 / $3 1M 1308.374 [1284.2, 1332.5] 151.58 · 不稳 Proprietary
4
gemini-2.5-flash-preview-09-2025 Google · Proprietary
1291±30.3 81 - 107 313 $0.30 / $2.50 1M 1291.475 [1261.2, 1321.8] 238.85 · 不稳 Proprietary
5
gpt-5.1 OpenAI · Proprietary
1284±22.9 40 - 58 753 $1.25 / $10 400K 1283.987 [1261.1, 1306.9] 136.11 · 不稳 Proprietary
6
kimi-k2.5-thinking 月之暗面 · Modified MIT
1271±34.7 25 - 47 276 $0.60 / $3 Unknown 1271.435 [1236.8, 1306.1] 312.59 · 不稳 Modified MIT
7
gpt-5.1-high OpenAI · Proprietary
1269±22.5 21 - 40 684 $1.25 / $10 400K 1269.282 [1246.8, 1291.8] 132.14 · 不稳 Proprietary
8
gemini-2.5-pro Google · Proprietary
1267±13.0 29 - 47 2.8K $1.25 / $10 1M 1266.539 [1253.5, 1279.6] 44.18 · 不稳 Proprietary
9
chatgpt-4o-latest-20250326 OpenAI · Proprietary
1265±16.5 33 - 53 1.2K $5 / $15 128K 1264.638 [1248.1, 1281.1] 70.88 · 不稳 Proprietary
10
gpt-5.2 OpenAI · Proprietary
1259±35.9 40 - 59 289 $1.75 / $14 400K 1259.015 [1223.1, 1294.9] 335.05 · 不稳 Proprietary
11
claude-opus-4-20250514 Anthropic · Proprietary
1256±30.6 70 - 96 216 $15 / $75 200K 1256.012 [1225.4, 1286.6] 243.16 · 不稳 Proprietary
12
ernie-5.0-preview-1220 百度 · Proprietary
1254±29.3 448 1253.694 [1224.4, 1283.0] 223.84 · 不稳 Proprietary
13
gemini-2.5-flash Google · Proprietary
1252±13.9 71 - 96 2.0K $0.30 / $2.50 1M 1252.450 [1238.5, 1266.4] 50.57 · 不稳 Proprietary
14
qwen3.5-397b-a17b 阿里巴巴 · Apache 2.0
1247±43.6 28 - 52 183 $0.39 / $2.34 262.1K 1247.116 [1203.5, 1290.8] 495.84 · 不稳 Apache 2.0
15
grok-4-0709 xAI · Proprietary
1243±17.8 71 - 100 1.3K $3 / $15 256K 1243.405 [1225.6, 1261.2] 82.76 · 不稳 Proprietary
16
kimi-k2.5-instant 月之暗面 · Modified MIT
1243±40.0 44 - 74 202 $0.44 / $2 262.1K 1242.967 [1203.0, 1282.9] 415.49 · 不稳 Modified MIT
17
qwen3-vl-235b-a22b-instruct 阿里巴巴 · Apache 2.0
1234±19.9 61 - 93 840 $0.20 / $0.88 262.1K 1233.835 [1213.9, 1253.8] 103.51 · 不稳 Apache 2.0
18
gpt-5.2-high OpenAI · Proprietary
1231±35.2 37 - 57 278 $1.75 / $14 400K 1231.202 [1196.0, 1266.4] 323.36 · 不稳 Proprietary
19
gpt-5-chat OpenAI · Proprietary
1227±17.1 51 - 80 1.3K $1.25 / $10 128K 1227.381 [1210.3, 1244.5] 76.29 · 不稳 Proprietary
20
gpt-4.1-2025-04-14 OpenAI · Proprietary
1222±17.1 69 - 93 1.4K $2 / $8 1M 1221.942 [1204.8, 1239.1] 76.51 · 不稳 Proprietary
21
o3-2025-04-16 OpenAI · Proprietary
1217±15.5 48 - 69 1.7K $2 / $8 200K 1216.736 [1201.2, 1232.3] 62.77 · 不稳 Proprietary
22
claude-3-7-sonnet-20250219-thinking-32k Anthropic · Proprietary
1213±37.6 106 - 127 142 $3 / $15 200K 1212.951 [1175.3, 1250.6] 368.21 · 不稳 Proprietary
23
mistral-medium-2508 Mistral · Proprietary
1207±15.8 74 - 98 1.5K $2.70 / $8.10 32K 1206.755 [1191.0, 1222.5] 64.72 · 不稳 Proprietary
24
gemini-2.5-flash-lite-preview-09-2025-no-thinking Google · Proprietary
1207±30.2 116 - 132 322 $0.10 / $0.40 1M 1206.539 [1176.3, 1236.7] 237.59 · 不稳 Proprietary
25
gemini-2.0-flash-001 Google · Proprietary
1203±32.6 135 - 156 295 $0.10 / $0.40 1M 1202.597 [1170.0, 1235.2] 277.34 · 不稳 Proprietary
26
claude-sonnet-4-20250514 Anthropic · Proprietary
1200±36.6 102 - 126 173 $3 / $15 1M 1199.569 [1162.9, 1236.2] 349.08 · 不稳 Proprietary
27
gpt-5-high OpenAI · Proprietary
1197±16.4 45 - 65 1.5K $1.25 / $10 400K 1197.051 [1180.7, 1213.4] 69.74 · 不稳 Proprietary
28
gpt-5-mini-high OpenAI · Proprietary
1196±19.8 101 - 126 1.0K $0.25 / $2 400K 1196.125 [1176.4, 1215.9] 101.62 · 不稳 Proprietary
29
mistral-small-2506 Mistral · Apache 2.0
1193±27.0 137 - 163 482 $0.10 / $0.30 32K 1192.543 [1165.6, 1219.5] 189.55 · 不稳 Apache 2.0
30
qwen3-vl-235b-a22b-thinking 阿里巴巴 · Apache 2.0
1191±44.4 91 - 123 164 $0.26 / $2.60 131.1K 1191.332 [1146.9, 1235.8] 513.69 · 不稳 Apache 2.0
31
gpt-4.1-mini-2025-04-14 OpenAI · Proprietary
1190±18.0 111 - 131 1.3K $0.40 / $1.60 1M 1190.430 [1172.4, 1208.4] 84.37 · 不稳 Proprietary
32
gemini-2.5-flash-lite-preview-06-17-thinking Google · Proprietary
1188±18.1 122 - 137 1.3K $0.10 / $0.40 1M 1188.000 [1169.9, 1206.1] 85.00 · 不稳 Proprietary
33
gemma-3-27b-it Google · Gemma
1187±23.3 131 - 147 636 $0.08 / $0.16 131.1K 1186.776 [1163.5, 1210.1] 141.14 · 不稳 Gemma
34
o4-mini-2025-04-16 OpenAI · Proprietary
1179±17.2 102 - 126 1.4K $1.10 / $4.40 200K 1179.004 [1161.8, 1196.2] 76.95 · 不稳 Proprietary
35
mistral-medium-2505 Mistral · Proprietary
1166±24.1 105 - 127 559 $0.40 / $2 131.1K 1165.562 [1141.4, 1189.7] 151.59 · 不稳 Proprietary
36
glm-4.6v 智谱 ZAI · MIT
1155±40.2 107 - 142 236 $0.30 / $0.90 131.1K 1155.026 [1114.8, 1195.2] 420.54 · 不稳 MIT
37
llama-4-scout-17b-16e-instruct Meta · Llama
1140±40.2 179 - 206 236 $0.40 / $0.70 8.2K 1140.298 [1100.1, 1180.5] 419.96 · 不稳 Llama
38
mistral-small-3.1-24b-instruct-2503 Mistral · Apache 2.0
1137±21.5 207 - 221 847 $0.10 / $0.30 32K 1137.077 [1115.6, 1158.5] 119.87 · 不稳 Apache 2.0
39
llama-4-maverick-17b-128e-instruct Meta · Llama 4
1117±40.2 173 - 200 221 $0.63 / $1.80 131.1K 1116.812 [1076.6, 1157.0] 420.57 · 不稳 Llama 4

没有找到相关模型