| 排名 | 模型名称 | ArenaElo | CodingElo | Vision | ArenaHard |
|---|---|---|---|---|---|
| 1 | Gemini-2.5-Pro-Preview-05 | 1480 | 1492 | 1347 | 96.4 |
| 2 | Gemini-2.5-Pro | 1474 | 1480 | 1336 | 70.5 |
| 3 | GPT-5 | 1462 | 1502 | 1297 | 68 |
| 4 | Gemini-2.5-Pro-Preview-06 | 1443 | 1461 | 1379 | 96.4 |
| 5 | Gemini-2.5-Pro-Exp-03-25 | 1438 | 1422 | 1342 | 0 |
| 6 | Grok-4-0709 | 1428 | 1451 | 1284 | 78.2 |
| 7 | GLM-4.5 | 1423 | 1466 | 0 | 56 |
| 8 | Qwen3-Max-Preview | 1421 | 1466 | 0 | 65 |
| 9 | Qwen3-235B-A22B-Instruct-2507 | 1426 | 1463 | 0 | 51 |
| 10 | ClaudeOpus-4.0(thinking-16k) | 1422 | 1471 | 0 | 61 |
| 11 | DeepSeek-R1-052820 | 1424 | 1425 | 084 | 93.2 |
| 12 | Gemini-2.5-Flash-Preview-0520 | 1420 | 1429 | 1302 | 0 |
| 13 | DeepSeek-V3.1 | 1420 | 1435 | 0 | 49 |
| 14 | ClaudeOpus-4.1 | 1419 | 1465 | 0 | 49 |
| 15 | Gemini-2.5-Flash | 1417 | 1423 | 1298 | 65.1 |
| 16 | DeepSeek-V3.1-thinking | 1417 | 1437 | 0 | 60 |
| 17 | Qwen3-235B-A22B-Thinking-2507 | 1413 | 1442 | 0 | 64 |
| 18 | GPT-5-chat | 1413 | 1421 | 1288 | 67 |
| 19 | os-2025-04-16 | 1411 | 1426 | 1307 | 0 |
| 20 | ChatGPT-4o-latest(2025-03-26) | 1408 | 1431 | 1312 | 0 |
| 21 | Grok-3-Preview-0224 | 1406 | 1411 | 0 | 0 |
| 22 | chocolate (Early Grok-3) | 1402 | 1399 | 0 | 0 |
| 23 | Mistral-Medium-3.1 | 1402 | 1412 | 0 | 40 |
| 24 | GPT-4.5-Preview | 1400 | 1408 | 0 | 0 |
| 25 | Hunyuan-T1-20250711 | 1400 | 1409 | 0 | 0 |
| 26 | MAI-1-Preview | 1393 | 1406 | 0 | 0 |
| 27 | Gemini-2.5-Flash-Preview-0417 | 1394 | 1402 | 1274 | 0 |
| 28 | GLM-4.5-Air | 1393 | 1421 | 0 | 49 |
| 29 | Qwen3-235B-A22B-no-thinking | 1387 | 1405 | 0 | 95.6 |
| 30 | Gemini-2.0-Flash-Thinking-Exp-01-21 | 1385 | 1368 | 1280 | 0 |
| 31 | Kimi-K2-0905-Preview | 1382 | 1403 | 0 | 51 |
| 32 | Qwen-VL-Max-2025-08-13 | 1381 | 1440 | 1263 | 0 |
| 33 | Qwen3-30B-A38-Instruct-2507 | 1380 | 1419 | 0 | 46 |
| 34 | Gemini-2.0-Pro-Exp-02-05 | 1379 | 1372 | 1252 | 0 |
| 35 | ChatGPT-4o-latest(2025-01-29) | 1377 | 1360 | 1276 | 0 |
| 36 | Gemini-2.5-Flash-Lite-Preview-0617-Thinking | 1377 | 1388 | 1231 | 0 |
| 37 | GPT-5-mini | 1375 | 1419 | 1264 | 64 |
| 38 | kimi-k2-0711-preview | 1374 | 1392 | 0 | 57.6 |
| 39 | ClaudeOpus-4.0(20250514) | 1373 | 1414 | 1231 | 0 |
| 40 | Hunyuan-Turbo5-20250416 | 1373 | 1376 | 0 | 0 |
| 41 | ClaudeOpus-4 (thinking-16k) | 1371 | 1426 | 1240 | 64.4 |
| 42 | DeepSeek-V3-0324 | 1370 | 1387 | 0 | 0 |
| 43 | GPT-4.1-2025-04-14 | 1367 | 1373 | 1280 | 0 |
| 44 | Mistral-Medium-3 | 1365 | 1387 | 0 | 0 |
| 45 | Minimax-M1 | 1364 | 1368 | 0 | 63 |
| 46 | DeepSeek-R1 | 1361 | 1362 | 0 | 0 |
| 47 | Grok-3-Mini-beta | 1361 | 1387 | 0 | 0 |
| 48 | Grok-3-mini-high | 1361 | 1372 | 0 | 66.7 |
| 49 | Step-3 | 1360 | 1400 | 1240 | 0 |
| 50 | Qwen3-Coder-480B-A38-Instruct | 1358 | 1404 | 0 | 45 |
| 51 | Gemini-2.0-Flash-001 | 1356 | 1353 | 1243 | 0 |
| 52 | Gemini-2.0-Flash-Exp | 1355 | 1353 | 1257 | 0 |
| 53 | o1-2024-12-17 | 1353 | 1363 | 0 | 90.4 |
| 54 | o4-mini-2025-04-16 | 1351 | 1373 | 1262 | 0 |
| 55 | ClaudeSonnet-4 (thinking-32k) | 1351 | 1409 | 1241 | 62.8 |
| 56 | ClaudeSonnet-4 (20250514) | 1346 | 1385 | 1221 | 0 |
| 57 | Qwen3-32B | 1344 | 1376 | 0 | 59.2 |
| 58 | Qwen3-235B-A22B | 1342 | 1365 | 0 | 95.6 |
| 59 | Llama-3.3-Nextroton-Super-49B-v1.5 | 1339 | 1352 | 0 | 52 |
| 60 | step-10-Turbo-202506 | 1339 | 1361 | 1232 | 0 |
| 61 | Gamma-3-7B-it | 1338 | 1306 | 0 | 0 |
| 62 | Mistral-Small-3.2-2506 | 1337 | 1361 | 1195 | 32 |
| 63 | Mistral-Small-2506 | 1335 | 1365 | 1207 | 42.3 |
| 64 | GPT-5-nano | 1333 | 1383 | 1216 | 54 |
| 65 | Qwen2.5-Max | 1332 | 1385 | 0 | 0 |
| 66 | Q3-mini-high | 1326 | 1364 | 0 | 0 |
| 67 | Amazon-Nova-Experimental-Chat-0514 | 1325 | 1342 | 0 | 42.6 |
| 68 | GPT-4.1-mini-2025-04-14 | 1324 | 1361 | 1235 | 0 |
| 69 | Gamma-3-12B-it | 1322 | 1287 | 0 | 0 |
| 70 | Amazon-Nova-Chat-0514 | 1322 | 1335 | 0 | 35 |
| 71 | Qwen3-30B-A38 | 1321 | 1346 | 0 | 55.6 |
| 72 | Llama-3.1-Nextroton-Ultra-25B-v1 | 1321 | 1345 | 0 | 60.8 |
| 73 | DeepSeek-V3 | 1317 | 1317 | 0 | 0 |
| 74 | Qwen2.5-Plus-0125 | 1313 | 1316 | 0 | 0 |
| 75 | QW-32B | 1312 | 1329 | 0 | 0 |
| 76 | Command-AI (03-2025) | 1312 | 1318 | 0 | 0 |
| 77 | Gemini-2.0-Flash-Lite-Preview-0205 | 1310 | 1322 | 1153 | 0 |
| 78 | QwenPlus-0125 | 1310 | 1320 | 0 | 0 |
| 79 | Gemini-2.0-Flash-Lite | 1309 | 1319 | 1152 | 0 |
| 80 | GLM-4-Plus-0111 | 1308 | 1291 | 0 | 0 |
| 81 | Q3-mini | 1305 | 1355 | 0 | 0 |
| 82 | o1-mini | 1304 | 1353 | 0 | 92 |
| 83 | Step-1-16k-Exp | 1304 | 1266 | 0 | 0 |
| 84 | Hunyuan-Turbo5-20250226 | 1303 | 1316 | 0 | 0 |
| 85 | Gamma-3-14B-it | 1303 | 1279 | 0 | 0 |
| 86 | Gemini-1.5-Pro-002 | 1302 | 1280 | 1221 | 0 |
| 87 | Claude-3.7-Sonnet (thinking-32k) | 1302 | 1332 | 0 | 0 |
| 88 | Claude-3.7-Sonnet | 1300 | 1342 | 1225 | 0 |
| 89 | Hunyuan-Turbo-0102 | 1295 | 1316 | 0 | 0 |
| 90 | Llama-3.3-Nextroton-Super-49B-v1 | 1294 | 1293 | 0 | 88.3 |
| 91 | GLM-4-Plus | 1292 | 1301 | 0 | 0 |
| 92 | Grok-2-0613 | 1293 | 1282 | 0 | 0 |
| 93 | yLightning | 1287 | 1303 | 0 | 81.5 |
| 94 | GPT-4o-2024-03-13 | 1285 | 1293 | 1206 | 79.21 |
| 95 | Claude-3.5-Sonnet (20240222) | 1284 | 1325 | 1184 | 85.2 |
| 96 | Claude-3.5-Sonnet (20240207) | 1283 | 1309 | 1167 | 29 |
| 97 | Qwen-Max-0919 | 1279 | 1295 | 0 | 0 |
| 98 | Athena-v2-Chat-72B | 1275 | 1300 | 0 | 85 |
| 99 | Gamma-3-4B-it | 1274 | 1264 | 0 | 0 |
声明：本文来自猫目，版权归作者所有。文章内容仅代表作者独立观点，不代表数字化转型网立场，转载目的在于传递更多信息。如有侵权，请联系我们。
