Atlas

Benchmarks

← All benchmarks

LMArena Text Arena Occupational Business, Management & Financial Ops 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
Gemini 4 Argon1509
Opus 4.71508
Muse Spark 1.21502
Muse Spark 1.31501
Claude Fable 51500
Opus 4.61500
Muse Wonder1498
Claude Opus 5.51494
Muse Spark 1.11491
GPT-5.51490
Muse Spark1490
Opus 4.81489
Kimi K31487
GPT-5.6 Sol1487
GPT-6.1 Sol1485
Claude Opus 51485
Qwen3.8-Max1485
Claude Fable 5.11485
Gemini 3.7 Flash1484
GPT-5.41482
Sonnet 4.61482
Gemini 3.8 Flash1481
Gemini 3.1 Pro Preview1478
DeepSeek V4.1 Flash1477
Claude Sonnet 5.51476
ERNIE 5.11475
Gemini 3 Pro Preview1474
GLM-5.31474
GPT-6 Astra1473
Gemini 3.6 Flash1473
Opus 4.51472
MiMo-V2.5-Pro1471
GLM-5.3 Flash1470
Gemini 3 Flash Preview1469
Gemini 3.5 Flash1468
DeepSeek V4 Pro 08131467
GPT-5.6 Terra1467
GLM-5.21466
Sonnet 51466
Grok 4.51466
Loading Atlas data…