Atlas

Benchmarks

← All benchmarks

LMArena Text Arena Multi-turn Elo

Chat & Writing · 2024-06-29

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)

ModelScore
Gemini 4 Argon1544
Muse Wonder1519
Claude Fable 51517
Opus 4.61516
Opus 4.71516
Muse Spark 1.21511
Gemini 3.8 Flash1504
Claude Opus 5.51503
Kimi K31502
Opus 4.81497
Gemini 3.1 Pro Preview1496
Gemini 3 Pro Preview1496
Muse Spark 1.11496
Muse Spark 1.31494
Muse Spark1493
Qwen3.8-Max1493
GPT-5.41493
GPT-5.6 Sol1490
Gemini 3.7 Flash1489
Gemini 3.6 Flash1488
Claude Fable 5.11488
GPT-5.51487
Claude Opus 51487
GPT-6 Astra1485
Opus 4.51484
GPT-6.1 Sol1483
Qwen3.7 Max Preview1482
Gemini 3 Flash Preview1482
Sonnet 4.61481
Gemini 3.5 Flash1480
MiMo-V2.5-Pro1480
GLM-5.31478
GLM-5.11478
Sonnet 4.51477
GLM-5.3 Flash1476
GLM-5.21475
DeepSeek-V4-Pro1475
Claude Sonnet 5.51474
Sonnet 51473
Grok 4.51473
Loading Atlas data…