Through an API

Open and closed models answer the same suite-standard 1.0 through their APIs, ranked together. 1 ranked model.

#ModelPass rate
1DeepSeek V4.1 Flash 1017Open weights100%

Model leaderboard

191 models in non-english ranked by LMArena score · updated Nov 11, 2026

#ModelScore
1Gemini 4 Carbon (High)Closed. Closed weights: ranked by its LMArena score, with no size or downloads to show.1534
2Gemini 4 Argon (High)Closed. Closed weights: ranked by its LMArena score, with no size or downloads to show.1523
3Claude Fable 5.1 (Max)Closed. Closed weights: ranked by its LMArena score, with no size or downloads to show.1507
4Claude Opus 5.5 (High)Closed. Closed weights: ranked by its LMArena score, with no size or downloads to show.1503
5Claude Opus 5 (Max)Closed. Closed weights: ranked by its LMArena score, with no size or downloads to show.1500
6Claude Opus 5 (High)Closed. Closed weights: ranked by its LMArena score, with no size or downloads to show.1495
7Gemini 4 Hydrogen (High)Closed. Closed weights: ranked by its LMArena score, with no size or downloads to show.1495
8Gemini 3.8 Flash (High)Closed. Closed weights: ranked by its LMArena score, with no size or downloads to show.1492
9Muse Wonder (Max)Closed. Closed weights: ranked by its LMArena score, with no size or downloads to show.1491
10Claude Opus 4.6 (High)Closed. Closed weights: ranked by its LMArena score, with no size or downloads to show.1487
11Gemini 3.7 Flash (High)Closed. Closed weights: ranked by its LMArena score, with no size or downloads to show.1486
12Claude Opus 4.6Closed. Closed weights: ranked by its LMArena score, with no size or downloads to show.1484
13Muse Spark 1.3 (Max)Closed. Closed weights: ranked by its LMArena score, with no size or downloads to show.1483
14Claude Fable 5 (High)Closed. Closed weights: ranked by its LMArena score, with no size or downloads to show.1482
15Claude Opus 4.7 (High)Closed. Closed weights: ranked by its LMArena score, with no size or downloads to show.1481
16Muse Spark 1.2 (xHigh)Closed. Closed weights: ranked by its LMArena score, with no size or downloads to show.1478
17Gemini 3.5 Flash (High)Closed. Closed weights: ranked by its LMArena score, with no size or downloads to show.1477
18Gemini 3.1 Pro PreviewClosed. Closed weights: ranked by its LMArena score, with no size or downloads to show.1476
19Qwen3.8-MaxClosed. Closed weights: ranked by its LMArena score, with no size or downloads to show.1475
20Gemini 3 ProClosed. Closed weights: ranked by its LMArena score, with no size or downloads to show.1474
Show all 191 models

Scores: LMArena, CC BY 4.0. Measured on served versions, not local builds. A model with several served variants shows its best.