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
Opus 4.61518
Opus 4.71517
Claude Fable 51517
Opus 4.81505
Kimi K31503
Muse Spark 1.11502
Gemini 3 Pro Preview1495
GPT-5.41495
Gemini 3.1 Pro Preview1492
Muse Spark1492
GPT-5.51490
GPT-5.6 Sol1489
Gemini 3.5 Flash1489
Gemini 3.6 Flash1486
Claude Opus 51486
Opus 4.51484
Gemini 3 Flash Preview1483
Qwen3.7 Max Preview1483
GLM-5.11483
Sonnet 4.61480
Sonnet 4.51479
GPT-5.6 Terra1478
MiMo-V2.5-Pro1477
DeepSeek-V4-Pro1475
ERNIE 5.11473
GLM-51472
Grok 4.51472
GLM-5.21471
GPT-5.4 Mini1470
MiMo-V2-Pro1469
Sonnet 51469
Qwen3.7-Plus1469
Opus 4.11468
GPT-5.3 Instant1468
Hy31464
Gemma 4 31B1464
Grok 4.11463
GPT-5.11463
GPT-5.6 Luna1462
Gemini 3.5 Flash-Lite1462
Loading Atlas data…