LMArena Text Math No Style Control Elo
Math · 2024-09-09
Category-specific Elo score from the LMArena text-arena voting leaderboard. Higher Elo indicates stronger crowd-voted preference within this category.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Opus 5 | 1564 |
| Claude Fable 5 | 1529 |
| Gemini 3.5 Flash | 1525 |
| Gemini 3.6 Flash | 1523 |
| Opus 4.6 | 1518 |
| Opus 4.7 | 1498 |
| Qwen3.7 Max Preview | 1494 |
| GPT-5.4 | 1489 |
| Gemini 3.1 Pro Preview | 1489 |
| Opus 4.8 | 1485 |
| GPT-5.5 | 1485 |
| GLM-5.1 | 1479 |
| ERNIE 5.1 | 1479 |
| Muse Spark 1.1 | 1477 |
| Gemini 3 Pro Preview | 1476 |
| MiMo-V2.5-Pro | 1476 |
| Grok 4.5 | 1475 |
| Inkling | 1475 |
| Kimi K2.6 | 1474 |
| Gemini 3 Flash Preview | 1474 |
| GLM-5.2 | 1471 |
| Qwen3.7-Plus | 1470 |
| Kimi K2.5 | 1469 |
| Gemma 4 26B A4B | 1467 |
| Gemma 4 31B | 1466 |
| Sonnet 5 | 1464 |
| Sonnet 4.6 | 1462 |
| GPT-5.6 Sol | 1460 |
| GPT-5.6 Terra | 1460 |
| Opus 4.5 | 1459 |
| GPT-5.6 Luna | 1454 |
| GLM 5V Turbo | 1452 |
| Muse Spark | 1451 |
| Qwen3.6 Plus (2026-04-02) | 1451 |
| Gemini 2.5 Pro | 1450 |
| Qwen3 Max Preview | 1450 |
| Qwen3.5 397B A17B | 1450 |
| MiMo-V2-Pro | 1448 |
| GPT-5.1 | 1443 |
| DeepSeek-V4-Pro | 1443 |