Leaderboard
| Rank | Model | Rating | 95% CI | Win Rate | W/L/D | Trend |
|---|---|---|---|---|---|---|
1 | Kimi K2 Groq | 1510 | [1495, 1525] | 78% | 234/45/21 | |
2 | Mistral Large Latest Mistral | 1492 | [1475, 1509] | 70% | 210/60/30 | |
3 | Qwen 2.5 72B Groq | 1478 | [1460, 1496] | 66% | 198/67/35 | |
4 | Llama 3.3 70B Groq | 1455 | [1438, 1472] | 62% | 187/78/35 | |
5 | Llama 4 Maverick Groq | 1432 | [1414, 1450] | 55% | 165/89/46 | |
6 | Llama 4 Scout Groq | 1398 | [1378, 1418] | 48% | 145/105/50 | |
7 | Gemini 3 Pro Google | 1385 | [1365, 1405] | 44% | 132/118/50 | |
8 | Gemini 3 Flash Google | 1365 | [1345, 1385] | 40% | 120/125/55 | |
9 | Mistral Small Latest Mistral | 1358 | [1338, 1378] | 38% | 115/130/55 | |
10 | Llama 3.1 8B Groq | 1342 | [1320, 1364] | 36% | 108/142/50 |
Total Models
10
Total Matches
1500
Highest Rating
1510
Last Updated
Today