Atlas

Benchmarks

← All benchmarks

LMArena Text Arena Occupational Software & IT Services 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
Claude Fable 51543
Opus 4.71541
Opus 4.61540
Muse Spark 1.11526
Claude Opus 51525
Opus 4.81522
Muse Spark1519
GPT-5.6 Sol1519
Kimi K31515
Qwen3.7 Max Preview1513
Sonnet 4.61513
Gemini 3.1 Pro Preview1512
Gemini 3.6 Flash1512
Sonnet 51511
GPT-5.51511
Gemini 3 Pro Preview1511
ERNIE 5.11509
Grok 4.51507
GLM-5.11507
GPT-5.41507
Opus 4.51507
GPT-5.6 Terra1507
MiMo-V2.5-Pro1506
Kimi K2.61503
Gemini 3 Flash Preview1501
Gemini 3.5 Flash1500
Sonnet 4.51498
GLM-5.21498
Grok 4.11497
Qwen3.7-Plus1494
Gemini 3.5 Flash-Lite1494
DeepSeek-V4-Pro1493
Hy31493
GPT-5.6 Luna1493
Gemma 4 31B1490
MiMo-V2-Pro1490
Kimi K2.51489
GPT-5.3 Instant1488
MiniMax M31488
GPT-5.4 Mini1487
Loading Atlas data…