Atlas

Benchmarks

← All benchmarks

LMArena Text Arena Occupational Life, Physical, and Social Science Elo

Professional Work · 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)

ModelScore
Kimi K31537
Claude Fable 51529
Opus 4.61529
Opus 4.71525
Claude Opus 51516
Gemini 3.1 Pro Preview1508
Opus 4.81506
Muse Spark 1.11505
Gemini 3.6 Flash1499
Sonnet 4.61499
Gemini 3 Pro Preview1498
Muse Spark1498
GPT-5.51498
Gemini 3.5 Flash1496
Hy31494
GLM-5.21493
MiMo-V2.5-Pro1490
GLM-5.11489
GPT-5.41488
ERNIE 5.11487
Qwen3.7 Max Preview1487
Opus 4.51487
Grok 4.51486
Gemini 3 Flash Preview1486
Sonnet 51485
Gemini 3.5 Flash-Lite1482
DeepSeek-V4-Pro1481
Grok 4.11480
MiMo-V2-Pro1479
GLM-51479
Kimi K2.61478
GPT-5.6 Sol1477
Gemma 4 31B1473
Qwen3.7-Plus1472
Sonnet 4.51472
Kimi K2.51471
GLM-4.71471
Gemini 2.5 Pro1470
GPT-5.11467
MiniMax M31467
Loading Atlas data…