Valumigo

LMArena · French

We regularly fetch and display public benchmark data: LMArena user voting rankings, Epoch AI test scores, and OpenRouter usage rankings. Each leaderboard shows both its publication date and the date we retrieved it. These scores are not assigned by this site.

LMArena scores come from people comparing two models' answers side by side and voting for the better one, using an Elo-based system. If score differences fall within the confidence intervals, treat the models as roughly comparable.

How to read this leaderboard

What it measures: A ranking calculated from votes on questions classified as French in LMArena text conversations.

How to read the score: Shows which models voters preferred for questions in French. The question's language does not indicate the voter's native language or identity.

Caveats: Vote counts and confidence interval widths vary by language and model. For new models, check vote counts, update dates and aggregation conditions together.

Insights from this ranking

  • The 95% confidence intervals for 1st-place muse-spark-1.3-max and 2nd-place claude-fable-5-high overlap. This aggregation alone does not clearly establish their order.
  • 54 other models have confidence intervals that overlap with the 1st-place model's. Interpret small ranking differences cautiously alongside vote counts.
  • Anthropic has the most models among the top 10, with 5.
  • The 1st-place model received 333 votes, and this leaderboard includes 290 models.

French LMArena

Published 2026-10-02 · Retrieved 2026-10-04

14701500153015601590
Metamuse-spark-1.3-max
1534
Anthropicclaude-fable-5-high
1525
Metamuse-spark
1521
Anthropicclaude-opus-4-7-high
1519
Metamuse-spark-1.1
1517
Anthropicclaude-fable-5.1-max
1514
Googlegemini-3.6-flash-high
1513
Googlegemini-3.7-flash-high
1511
Anthropicclaude-opus-4-6-high
1510
Zglm-5.3-max
1510
Ogpt-5.6-sol-xhigh
1510
Moonshot AIkimi-k3-max
1509
Anthropicclaude-opus-4-8-high
1508
Zglm-5.3-flash
1507
Googlegemini-3-pro
1506
Anthropicclaude-opus-5-high
1506
Googlegemini-3.8-flash-high
1506
Alibabaqwen3.8-max
1505
xgrok-4.20-beta-0309-reasoning
1503
Googlegemini-3.1-pro-preview
1502

Dots show scores; horizontal lines show 95% confidence intervals. Overlapping intervals suggest similar performance. The chart shows only the highest-scoring reasoning setting, such as high or max, for each model. The table shows rankings for all settings. Chat and vision rankings use 'style and length adjustment (style control)', the same default as the LMArena website.

Top ranking by company

  • MetaMetamuse-spark-1.3-max#1
  • AnthropicAnthropicclaude-fable-5-high#2
  • GoogleGooglegemini-3.6-flash-high#7
  • ZZ.aiglm-5.3-max#11
  • OOpenAIgpt-5.6-sol-xhigh#12
  • Moonshot AIMoonshot AIkimi-k3-max#13
  • AlibabaAlibabaqwen3.8-max#19
  • xxAIgrok-4.20-beta-0309-reasoning#21
  • XiaomiXiaomimimo-v2.5-pro#31
View table (top 50)
RankModelDeveloperScore95% confidence intervalVotes
1#1Metamuse-spark-1.3-maxMeta15341501–1568333
2#2Anthropicclaude-fable-5-highAnthropic15251507–15441,276
3#3Metamuse-sparkMeta15211492–1549481
4#4Anthropicclaude-opus-4-7-highAnthropic15191505–15332,295
5#5Metamuse-spark-1.1Meta15171499–15361,219
6#6Anthropicclaude-fable-5.1-maxAnthropic15141482–1546379
7#7Googlegemini-3.6-flash-highGoogle15131493–15321,120
8#8Googlegemini-3.7-flash-highGoogle15111486–1536614
9#9Anthropicclaude-opus-4-7Anthropic15101496–15242,370
10#10Anthropicclaude-opus-4-6-highAnthropic15101496–15242,518
11#11Zglm-5.3-maxZ.ai15101483–1536532
12#12Ogpt-5.6-sol-xhighOpenAI15101490–15291,116
13#13Moonshot AIkimi-k3-maxMoonshot AI15091490–15291,012
14#14Anthropicclaude-opus-4-8-highAnthropic15081494–15232,173
15#15Zglm-5.3-flashZ.ai15071485–1530765
16#16Googlegemini-3-proGoogle15061486–1526968
17#17Anthropicclaude-opus-5-highAnthropic15061490–15221,759
18#18Googlegemini-3.8-flash-highGoogle15061483–1528789
19#19Alibabaqwen3.8-maxAlibaba15051483–1527778
20#20Anthropicclaude-opus-4-8Anthropic15041490–15192,208
21#21xgrok-4.20-beta-0309-reasoningxAI15031489–15182,225
22#22Googlegemini-3.1-pro-previewGoogle15021490–15133,972
23#23Ogpt-5.5OpenAI15011487–15152,508
24#24Ogpt-5.4-highOpenAI15001486–15142,396
25#25Anthropicclaude-opus-4-6Anthropic14971484–15112,682
26#26Ogpt-6-astra-maxOpenAI14971456–1537216
27#27Ogpt-5.5-highOpenAI14961482–15102,514
28#28Anthropicclaude-opus-5-maxAnthropic14961474–1518865
29#29Ogpt-5.6-terra-xhighOpenAI14951476–15141,146
30#30xgrok-4.20-beta1xAI14941473–1516861
31#31Xiaomimimo-v2.5-proXiaomi14931480–15072,587
32#32Ogpt-5.5-instantOpenAI14931473–15131,053
33#33Googlegemini-3-flashGoogle14921471–1514825
34#34xgrok-4.20-multi-agent-beta-0309xAI14921478–15072,272
35#35Googlegemini-3.5-flash-highGoogle14921475–15091,511
36#36xgrok-4.6-highxAI14911467–1516625
37#37Anthropicclaude-opus-4-5-20251101Anthropic14911476–15062,022
38#38Zglm-5.2-maxZ.ai14911474–15071,599
39#39Ogpt-6-sol-maxOpenAI14901452–1528252
40#40Anthropicclaude-opus-4-5-20251101-high-32kAnthropic14901468–1511845
41#41ByteDancedola-seed-2.0-proByteDance14881474–15022,588
42#42Zglm-5.1Z.ai14861471–15012,013
43#43Ogpt-6-luna-maxOpenAI14861448–1523265
44#44Baiduernie-5.1Baidu14861468–15031,514
45#45Ogpt-5.4OpenAI14851471–15002,411
46#46DeepSeekdeepseek-v4-proDeepSeek14851470–14992,205
47#47Anthropicclaude-sonnet-5-highAnthropic14841467–15011,472
48#48xgrok-4.1-thinkingxAI14841468–15001,718
49#49Ogpt-5.2-chat-latest-20260210OpenAI14831463–15031,048
50#50Ogpt-5.6-luna-xhighOpenAI14821464–15011,212

Data: LMArena leaderboard dataset (CC BY 4.0). Changes: Top 50 entries per leaderboard; scores are rounded. https://huggingface.co/datasets/lmarena-ai/leaderboard-datasetCompany logos are trademarks of their respective owners and are used only for identification (icons: Simple Icons).Data: Epoch AI — Capabilities & benchmarking (CC BY 4.0). https://epoch.ai/benchmarksSource: OpenRouter (openrouter.ai/rankings), as of 2026-10-04. Licensed under CC BY 4.0. https://openrouter.ai/rankings