Atlas

Benchmarks

← All benchmarks

LMArena Text Arena Occupational Medicine & Healthcare 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
Opus 4.71521
Opus 4.61520
Kimi K31519
Claude Fable 51510
Gemini 3 Pro Preview1509
Muse Spark1505
Grok 4.11502
Gemini 3.1 Pro Preview1500
Claude Opus 51500
Opus 4.81497
ERNIE 5.11495
Gemini 3.5 Flash1492
GLM-5.21492
Gemini 3.6 Flash1492
Sonnet 4.61490
Muse Spark 1.11489
Opus 4.51486
MiMo-V2.5-Pro1486
GLM-5.11486
Gemini 3 Flash Preview1485
GPT-5.51485
GLM-4.71481
GPT-5.3 Instant1481
GPT-5.6 Sol1480
Qwen3.7 Max Preview1479
Hy31478
DeepSeek-V4-Pro1478
GLM-51477
GPT-5.41476
DeepSeek-V3.2-Exp1475
O3 (2025-04-16)1475
Qwen3 Max Preview1474
Grok 4.51473
Opus 4.11473
Sonnet 4.51473
MiniMax M31472
Qwen3.7-Plus1472
Sonnet 51472
Kimi K2.61470
GPT-5.6 Terra1470
Loading Atlas data…