Atlas

Benchmarks

← All benchmarks

LMArena Text Arena Occupational Legal & Government 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
Muse Spark 1.21523
Gemini 4 Argon1514
Muse Wonder1511
Opus 4.71511
Claude Fable 51510
Opus 4.61509
Kimi K31509
Claude Opus 51504
Claude Opus 5.51503
Muse Spark 1.31502
Gemini 3 Pro Preview1501
Muse Spark1500
Gemini 3.1 Pro Preview1498
Opus 4.81498
Muse Spark 1.11497
GPT-5.6 Sol1497
GPT-6.1 Sol1497
Gemini 3.7 Flash1496
GPT-5.51495
GLM-5.21491
Gemini 3.8 Flash1491
Claude Fable 5.11491
GPT-5.41490
GPT-6 Astra1489
Qwen3.8-Max1489
Sonnet 4.61484
Gemini 3.5 Flash1484
Gemini 3 Flash Preview1483
Claude Sonnet 5.51483
Opus 4.51482
Gemini 3.6 Flash1481
DeepSeek V4 Pro 08131480
Qwen3.7 Max Preview1480
Grok 4.51478
GPT-5.6 Terra1475
Grok 4.11475
MiMo-V2.5-Pro1475
Sonnet 51475
GLM-5.31474
DeepSeek-V4-Pro1474
Loading Atlas data…