LMArena Text Arena Instruction Following Elo
Chat & Writing · 2024-07-30
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 5.5 | 1521 |
| Gemini 4 Argon | 1519 |
| Opus 4.6 | 1511 |
| Claude Fable 5 | 1507 |
| Opus 4.7 | 1502 |
| Claude Fable 5.1 | 1500 |
| Muse Wonder | 1497 |
| Claude Opus 5 | 1495 |
| Opus 4.8 | 1491 |
| GPT-5.6 Sol | 1491 |
| Gemini 3.8 Flash | 1490 |
| Kimi K3 | 1489 |
| Gemini 3.7 Flash | 1487 |
| Claude Sonnet 5.5 | 1485 |
| GPT-6.1 Sol | 1485 |
| Muse Spark 1.3 | 1485 |
| Gemini 3.1 Pro Preview | 1480 |
| GLM-5.3 | 1478 |
| GPT-5.5 | 1478 |
| DeepSeek V4.1 Flash | 1477 |
| Qwen3.8-Max | 1475 |
| Sonnet 4.6 | 1475 |
| Opus 4.5 | 1474 |
| GPT-6 Astra | 1473 |
| GLM-5.3 Flash | 1473 |
| Gemini 3.6 Flash | 1473 |
| Gemini 3 Pro Preview | 1473 |
| Muse Spark 1.2 | 1472 |
| Muse Spark 1.1 | 1472 |
| MiMo-V2.6-Pro | 1471 |
| GPT-5.4 | 1471 |
| GLM-5.2 | 1469 |
| MiMo-V2.5-Pro | 1467 |
| Sonnet 5 | 1466 |
| Gemini 3.5 Flash | 1466 |
| Qwen3.7 Max Preview | 1465 |
| Muse Spark | 1465 |
| GPT-5.6 Terra | 1464 |
| GLM-5.1 | 1462 |
| Sonnet 4.5 | 1462 |