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
Opus 4.61524
Claude Fable 51524
Opus 4.71516
Opus 4.81506
Claude Opus 51506
Kimi K31502
Gemini 3.1 Pro Preview1498
Qwen3.7 Max Preview1497
Sonnet 4.61494
Gemini 3 Pro Preview1492
Opus 4.51492
GPT-5.6 Sol1489
GPT-5.51487
Gemini 3.6 Flash1486
MiMo-V2.5-Pro1485
GPT-5.41484
GLM-5.11483
Grok 4.51483
Sonnet 4.51483
Sonnet 51482
Gemini 3.5 Flash1481
Muse Spark 1.11479
GLM-5.21479
Kimi K2.61476
Gemini 3 Flash Preview1475
Muse Spark1474
DeepSeek-V4-Pro1474
Opus 4.11472
Qwen3.7-Plus1471
GPT-5.6 Terra1470
GLM-51470
Hy31468
MiMo-V2-Pro1467
Gemma 4 31B1467
ERNIE 5.11465
Gemini 3.5 Flash-Lite1464
GPT-5.11459
Kimi K2.51458
Gemini 2.5 Pro1457
GPT-5.3 Instant1456
Loading Atlas data…