Atlas

Benchmarks

← All benchmarks

LMArena Text Arena Longer Query Elo

Chat & Writing · 2024-04-14

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 Argon1534
Claude Opus 5.51524
Claude Fable 51522
Opus 4.61521
Opus 4.71515
Claude Fable 5.11510
Gemini 3.8 Flash1510
Opus 4.81503
Claude Opus 51503
Kimi K31503
Muse Wonder1502
Gemini 3.7 Flash1501
Claude Sonnet 5.51499
Gemini 3.1 Pro Preview1499
GPT-5.6 Sol1498
Muse Spark 1.31497
MiMo-V2.6-Pro1494
Opus 4.51492
Sonnet 4.61492
Qwen3.8-Max1492
Qwen3.7 Max Preview1491
Gemini 3 Pro Preview1490
GPT-6 Astra1489
GPT-6.1 Sol1489
Muse Spark 1.21488
GPT-5.51487
GLM-5.21486
MiMo-V2.5-Pro1486
GLM-5.31486
Gemini 3.6 Flash1485
Gemini 3.5 Flash1482
Sonnet 4.51481
GPT-5.41481
GLM-5.3 Flash1481
Sonnet 51481
DeepSeek V4.1 Flash1481
GLM-5.11480
Muse Spark 1.11480
Grok 4.51480
Kimi K2.61477
Loading Atlas data…