排名 模型 得分
🥇
gemini-3-pro Google · Proprietary
1337±19.0 4 - 10 1.0K $2 / $12 1M 1337.000 [1318.0, 1356.0] 3.00 · 稳定 Proprietary
🥈
claude-opus-4-7 Anthropic · Proprietary
1326±43.0 1 - 9 195 $5 / $25 1M 1326.000 [1283.0, 1369.0] 15.00 · 不稳 Proprietary
🥉
claude-opus-4-6-thinking Anthropic · Proprietary
1322±37.0 1 - 6 267 $5 / $25 1M 1322.000 [1285.0, 1359.0] 14.00 · 不稳 Proprietary
4
claude-opus-4-7-thinking Anthropic · Proprietary
1307±41.0 1 - 6 199 $5 / $25 1M 1307.000 [1266.0, 1348.0] 21.00 · 不稳 Proprietary
5
gemini-3.1-pro-preview Google · Proprietary
1294±22.0 1 - 7 734 $2 / $12 1M 1294.000 [1272.0, 1316.0] 18.00 · 不稳 Proprietary
6
claude-opus-4-6 Anthropic · Proprietary
1283±32.0 1 - 6 327 $5 / $25 1M 1283.000 [1251.0, 1315.0] 25.00 · 不稳 Proprietary
7
grok-4.20-beta-0309-reasoning xAI · Proprietary
1282±32.0 7 - 15 369 $2 / $6 2M 1282.000 [1250.0, 1314.0] 25.00 · 不稳 Proprietary
8
gemini-3-flash Google · Proprietary
1281±17.0 8 - 21 1.3K $0.50 / $3 1M 1281.000 [1264.0, 1298.0] 22.00 · 不稳 Proprietary
9
gemini-3-flash (thinking-minimal) Google · Proprietary
1281±18.0 15 - 29 1.0K $0.50 / $3 1M 1281.000 [1263.0, 1299.0] 23.00 · 不稳 Proprietary
10
claude-sonnet-4-6 Anthropic · Proprietary
1276±35.0 15 - 30 302 $3 / $15 1M 1276.000 [1241.0, 1311.0] 31.00 · 不稳 Proprietary
11
grok-4.20-multi-agent-beta-0309 xAI · Proprietary
1271±32.0 8 - 21 356 $2 / $6 2M 1271.000 [1239.0, 1303.0] 31.00 · 不稳 Proprietary
12
chatgpt-4o-latest-20250326 OpenAI · Proprietary
1264±18.0 33 - 53 1.2K $5 / $15 128K 1264.000 [1246.0, 1282.0] 26.00 · 不稳 Proprietary
13
qwen3.5-397b-a17b 阿里巴巴 · Apache 2.0
1264±26.0 28 - 52 529 $0.39 / $2.34 262.1K 1264.000 [1238.0, 1290.0] 31.00 · 不稳 Apache 2.0
14
gemini-2.5-pro Google · Proprietary
1257±13.0 29 - 47 3.2K $1.25 / $10 1M 1257.000 [1244.0, 1270.0] 27.00 · 不稳 Proprietary
15
dola-seed-2.0-preview 字节跳动 · Proprietary
1256±41.0 213 1256.000 [1215.0, 1297.0] 39.00 · 不稳 Proprietary
16
gpt-5.4-mini-high OpenAI · Proprietary
1256±32.0 17 - 39 362 $2.50 / $15 1.1M 1256.000 [1224.0, 1288.0] 38.00 · 不稳 Proprietary
17
gpt-5.1 OpenAI · Proprietary
1251±23.0 40 - 58 696 $1.25 / $10 400K 1251.000 [1228.0, 1274.0] 33.00 · 不稳 Proprietary
18
claude-opus-4-20250514 Anthropic · Proprietary
1249±46.0 70 - 96 106 $15 / $75 200K 1249.000 [1203.0, 1295.0] 43.00 · 不稳 Proprietary
19
gemini-2.5-flash-preview-09-2025 Google · Proprietary
1245±33.0 81 - 107 297 $0.30 / $2.50 1M 1245.000 [1212.0, 1278.0] 38.00 · 不稳 Proprietary
20
gpt-5.1-high OpenAI · Proprietary
1244±23.0 21 - 40 637 $1.25 / $10 400K 1244.000 [1221.0, 1267.0] 35.00 · 不稳 Proprietary
21
kimi-k2.5-thinking 月之暗面 · Modified MIT
1241±23.0 25 - 47 684 $0.60 / $3 Unknown 1241.000 [1218.0, 1264.0] 33.00 · 不稳 Modified MIT
22
glm-5v-turbo 智谱 ZAI · Proprietary
1241±43.0 181 1241.000 [1198.0, 1284.0] 43.00 · 不稳 Proprietary
23
gpt-5.2-chat-latest-20260210 OpenAI · Proprietary
1238±27.0 8 - 20 533 $1.75 / $14 128K 1238.000 [1211.0, 1265.0] 36.00 · 不稳 Proprietary
24
grok-4-1-fast-reasoning xAI · Proprietary
1236±29.0 47 - 67 445 $0.20 / $0.50 2M 1236.000 [1207.0, 1265.0] 37.00 · 不稳 Proprietary
25
kimi-k2.5-instant 月之暗面 · Modified MIT
1236±36.0 44 - 74 248 $0.44 / $2 262.1K 1236.000 [1200.0, 1272.0] 41.00 · 不稳 Modified MIT
26
gpt-5.2-high OpenAI · Proprietary
1235±22.0 37 - 57 727 $1.75 / $14 400K 1235.000 [1213.0, 1257.0] 34.00 · 不稳 Proprietary
27
gemini-2.5-flash Google · Proprietary
1233±13.0 71 - 96 2.4K $0.30 / $2.50 1M 1233.000 [1220.0, 1246.0] 29.00 · 不稳 Proprietary
28
gemini-3.1-flash-lite-preview Google · Proprietary
1228±22.0 37 - 59 751 $0.25 / $1.50 1M 1228.000 [1206.0, 1250.0] 33.00 · 不稳 Proprietary
29
gpt-4.1-2025-04-14 OpenAI · Proprietary
1227±19.0 69 - 93 1.3K $2 / $8 1M 1227.000 [1208.0, 1246.0] 31.00 · 不稳 Proprietary
30
gpt-5.2 OpenAI · Proprietary
1227±23.0 40 - 59 710 $1.75 / $14 400K 1227.000 [1204.0, 1250.0] 34.00 · 不稳 Proprietary
31
qwen3.5-122b-a10b 阿里巴巴 · Apache 2.0
1222±28.0 60 - 88 438 $0.26 / $2.08 262.1K 1222.000 [1194.0, 1250.0] 37.00 · 不稳 Apache 2.0
32
qwen3.5-27b 阿里巴巴 · Apache 2.0
1220±32.0 77 - 108 357 $0.20 / $1.56 262.1K 1220.000 [1188.0, 1252.0] 40.00 · 不稳 Apache 2.0
33
gpt-5-chat OpenAI · Proprietary
1218±19.0 51 - 80 1.3K $1.25 / $10 128K 1218.000 [1199.0, 1237.0] 31.00 · 不稳 Proprietary
34
grok-4-0709 xAI · Proprietary
1214±19.0 71 - 100 1.3K $3 / $15 256K 1214.000 [1195.0, 1233.0] 32.00 · 不稳 Proprietary
35
gpt-4.1-mini-2025-04-14 OpenAI · Proprietary
1213±20.0 111 - 131 1.2K $0.40 / $1.60 1M 1213.000 [1193.0, 1233.0] 32.00 · 不稳 Proprietary
36
ernie-5.0-preview-1220 百度 · Proprietary
1212±31.0 383 1212.000 [1181.0, 1243.0] 37.00 · 不稳 Proprietary
37
o3-2025-04-16 OpenAI · Proprietary
1207±18.0 48 - 69 1.6K $2 / $8 200K 1207.000 [1189.0, 1225.0] 31.00 · 不稳 Proprietary
38
qwen3-vl-235b-a22b-instruct 阿里巴巴 · Apache 2.0
1204±21.0 61 - 93 821 $0.20 / $0.88 262.1K 1204.000 [1183.0, 1225.0] 33.00 · 不稳 Apache 2.0
39
mistral-medium-2508 Mistral · Proprietary
1197±17.0 74 - 98 1.5K $2.70 / $8.10 32K 1197.000 [1180.0, 1214.0] 28.00 · 不稳 Proprietary
40
mistral-small-2506 Mistral · Apache 2.0
1197±29.0 137 - 163 463 $0.10 / $0.30 32K 1197.000 [1168.0, 1226.0] 36.00 · 不稳 Apache 2.0
41
gemini-2.0-flash-001 Google · Proprietary
1191±38.0 135 - 156 249 $0.10 / $0.40 1M 1191.000 [1153.0, 1229.0] 38.00 · 不稳 Proprietary
42
gemini-2.5-flash-lite-preview-06-17-thinking Google · Proprietary
1188±20.0 122 - 137 1.2K $0.10 / $0.40 1M 1188.000 [1168.0, 1208.0] 27.00 · 不稳 Proprietary
43
gemini-2.5-flash-lite-preview-09-2025-no-thinking Google · Proprietary
1187±32.0 116 - 132 317 $0.10 / $0.40 1M 1187.000 [1155.0, 1219.0] 33.00 · 不稳 Proprietary
44
gpt-5-high OpenAI · Proprietary
1186±20.0 45 - 65 1.4K $1.25 / $10 400K 1186.000 [1166.0, 1206.0] 25.00 · 不稳 Proprietary
45
gemma-3-27b-it Google · Gemma
1179±25.0 131 - 147 633 $0.08 / $0.16 131.1K 1179.000 [1154.0, 1204.0] 25.00 · 不稳 Gemma
46
o4-mini-2025-04-16 OpenAI · Proprietary
1176±19.0 102 - 126 1.3K $1.10 / $4.40 200K 1176.000 [1157.0, 1195.0] 20.00 · 不稳 Proprietary
47
gpt-5.4-nano-high OpenAI · Proprietary
1165±34.0 77 - 109 339 $2.50 / $15 1.1M 1165.000 [1131.0, 1199.0] 24.00 · 不稳 Proprietary
48
gpt-5-mini-high OpenAI · Proprietary
1163±23.0 101 - 126 1.0K $0.25 / $2 400K 1163.000 [1140.0, 1186.0] 17.00 · 不稳 Proprietary
49
mistral-medium-2505 Mistral · Proprietary
1152±27.0 105 - 127 489 $0.40 / $2 131.1K 1152.000 [1125.0, 1179.0] 14.00 · 不稳 Proprietary
50
llama-4-scout-17b-16e-instruct Meta · Llama
1148±41.0 179 - 206 236 $0.40 / $0.70 8.2K 1148.000 [1107.0, 1189.0] 18.00 · 不稳 Llama
51
glm-4.6v 智谱 ZAI · MIT
1136±44.0 107 - 142 195 $0.30 / $0.90 131.1K 1136.000 [1092.0, 1180.0] 14.00 · 不稳 MIT
52
hunyuan-vision-1.5-thinking 腾讯 · Proprietary
1132±44.0 81 - 126 191 Free / N/A Unknown 1132.000 [1088.0, 1176.0] 14.00 · 不稳 Proprietary
53
mistral-small-3.1-24b-instruct-2503 Mistral · Apache 2.0
1123±24.0 207 - 221 789 $0.10 / $0.30 32K 1123.000 [1099.0, 1147.0] 7.00 · 波动 Apache 2.0
54
llama-4-maverick-17b-128e-instruct Meta · Llama 4
1113±42.0 173 - 200 212 $0.63 / $1.80 131.1K 1113.000 [1071.0, 1155.0] 10.00 · 波动 Llama 4

没有找到相关模型