Atlas

Benchmarks

← All benchmarks

Arena Text — Spanish (No Style Control)

Chat & Writing

Raw Arena rating for Spanish-language Text Arena prompts without style-control adjustment. Higher ratings indicate stronger preference in blind pairwise user votes.

Top models (higher is better)

ModelScore
Claude Opus 51522
Claude Fable 5.11519
Claude Opus 5.51509
Opus 4.61509
Gemini 4 Argon1508
Claude Fable 51495
Opus 4.71494
Gemini 3.7 Flash1493
Muse Spark 1.31493
Qwen3.8-Max1487
Gemini 3.8 Flash1485
Gemini 3.1 Pro Preview1480
Gemini 3.5 Flash1480
Muse Spark 1.21479
GLM-5.21478
Muse Wonder1477
Gemini 3.6 Flash1476
Kimi K31475
Gemini 2.5 Pro1474
ERNIE 5.11473
GLM-5.3 Flash1472
Gemini 3 Pro Preview1470
Muse Spark1470
Gemini 3 Flash Preview1469
Mistral Large 4 Preview1469
GLM-5.11469
GPT-5.51468
MiMo-V2.5-Pro1468
Opus 4.81465
Sonnet 4.61464
Kimi K2.61463
Muse Spark 1.11462
Qwen3 Max Preview1462
GLM-5.31461
DeepSeek V4.1 Flash1458
Sonnet 4.51458
Qwen3.7-Plus (source unspecified)1457
MiMo-V2-Pro1457
Hy31456
DeepSeek-V4-Pro1456
Loading Atlas data…