LMArena Text Arena Occupational Mathematical Elo
Math · 2025-11-05
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 | 1552 |
| Opus 4.6 | 1528 |
| Claude Fable 5 | 1520 |
| Opus 4.7 | 1513 |
| GPT-5.6 Sol | 1511 |
| Gemini 3.5 Flash | 1506 |
| Opus 4.8 | 1504 |
| Gemini 3.6 Flash | 1504 |
| GPT-5.5 | 1503 |
| GPT-5.4 | 1500 |
| Muse Spark 1.1 | 1499 |
| MiMo-V2.5-Pro | 1494 |
| GLM-5.2 | 1493 |
| Grok 4.5 | 1493 |
| ERNIE 5.1 | 1487 |
| Gemini 3.1 Pro Preview | 1487 |
| Kimi K2.6 | 1485 |
| GPT-5.6 Terra | 1485 |
| Sonnet 5 | 1485 |
| Sonnet 4.6 | 1484 |
| GLM-5.1 | 1483 |
| Gemini 3 Pro Preview | 1481 |
| Qwen3.7-Plus | 1481 |
| Kimi K2.5 | 1478 |
| Opus 4.5 | 1478 |
| GPT-5.6 Luna | 1478 |
| Gemma 4 26B A4B | 1475 |
| Gemma 4 31B | 1474 |
| Gemini 3 Flash Preview | 1471 |
| Qwen3.7 Max Preview | 1470 |
| MiMo-V2-Pro | 1470 |
| Muse Spark | 1469 |
| GPT-5.2 | 1464 |
| Inkling | 1462 |
| GPT-5.1 | 1461 |
| DeepSeek-V4-Pro | 1461 |
| Qwen3.5 397B A17B | 1460 |
| GLM-5 | 1457 |
| Qwen3.6 Plus (2026-04-02) | 1456 |
| MiMo-V2.5 | 1455 |