Valumigo

LMArena · English

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 English in LMArena text conversations.

How to read the score: Shows which models voters preferred for questions in English. 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 gemini-4-argon-high and 2nd-place claude-opus-4-6-high overlap. This aggregation alone does not clearly establish their order.
  • 3 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 6.
  • The 1st-place model received 1,928 votes, and this leaderboard includes 413 models.

English LMArena

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

146014801500152015401560
Googlegemini-4-argon-high
1533
Anthropicclaude-opus-4-6-high
1514
Anthropicclaude-fable-5-high
1513
Anthropicclaude-opus-4-7-high
1510
Anthropicclaude-opus-5.5-high
1506
Metamuse-spark-1.3-max
1499
Metamuse-spark-1.2 (xHigh)
1498
Googlegemini-3.8-flash-high
1498
Anthropicclaude-fable-5.1-max
1498
Metamuse-spark
1497
Ogpt-6.1-sol-max
1496
Xiaomimimo-v2.6-pro
1496
Moonshot AIkimi-k3-max
1495
Anthropicclaude-opus-5-high
1493
Anthropicclaude-sonnet-5.5-xhigh
1492
Alibabaqwen3.8-max
1492
Metamuse-spark-1.1
1491
Googlegemini-3.1-pro-preview
1490
Anthropicclaude-opus-4-8-high
1490
Zglm-5.3-max
1490

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

  • GoogleGooglegemini-4-argon-high#1
  • AnthropicAnthropicclaude-opus-4-6-high#2
  • MetaMetamuse-spark-1.3-max#8
  • OOpenAIgpt-6.1-sol-max#13
  • XiaomiXiaomimimo-v2.6-pro#14
  • Moonshot AIMoonshot AIkimi-k3-max#15
  • AlibabaAlibabaqwen3.8-max#18
  • ZZ.aiglm-5.3-max#23
  • DeepSeekDeepSeekdeepseek-v4.1-flash-max#24
View table (top 50)
RankModelDeveloperScore95% confidence intervalVotes
1#1Googlegemini-4-argon-highGoogle15331519–15471,928
2#2Anthropicclaude-opus-4-6-highAnthropic15141509–151934,324
3#3Anthropicclaude-fable-5-highAnthropic15131508–151916,474
4#4Anthropicclaude-opus-4-7-highAnthropic15101505–151530,082
5#5Anthropicclaude-opus-4-6Anthropic15071502–151136,805
6#6Anthropicclaude-opus-5.5-highAnthropic15061492–15201,719
7#7Anthropicclaude-opus-4-7Anthropic15011496–150630,422
8#8Metamuse-spark-1.3-maxMeta14991491–15084,928
9#9Metamuse-spark-1.2 (xHigh)Meta14981484–15121,805
10#10Googlegemini-3.8-flash-highGoogle14981491–150510,363
11#11Anthropicclaude-fable-5.1-maxAnthropic14981489–15064,793
12#12Metamuse-sparkMeta14971489–15046,673
13#13Ogpt-6.1-sol-maxOpenAI14961479–15131,149
14#14Xiaomimimo-v2.6-proXiaomi14961481–15111,487
15#15Moonshot AIkimi-k3-maxMoonshot AI14951489–150210,786
16#16Anthropicclaude-opus-5-highAnthropic14931488–149824,266
17#17Anthropicclaude-sonnet-5.5-xhighAnthropic14921475–15091,196
18#18Alibabaqwen3.8-maxAlibaba14921485–14999,003
19#19Metamuse-spark-1.1Meta14911486–149715,100
20#20Anthropicclaude-opus-5-maxAnthropic14911484–149711,702
21#21Googlegemini-3.1-pro-previewGoogle14901486–149453,727
22#22Anthropicclaude-opus-4-8-highAnthropic14901485–149527,922
23#23Zglm-5.3-maxZ.ai14901482–14977,223
24#24DeepSeekdeepseek-v4.1-flash-maxDeepSeek14891479–15003,237
25#25Ogpt-5.6-sol-xhighOpenAI14891483–149514,827
26#26Ogpt-6-astra-maxOpenAI14881478–14983,692
27#27Googlegemini-3-proGoogle14871482–149316,887
28#28Googlegemini-3.6-flash-highGoogle14871481–149315,114
29#29Googlegemini-3.7-flash-highGoogle14851478–14938,659
30#30Ogpt-5.5-highOpenAI14841480–148931,442
31#31Ogpt-5.5OpenAI14831478–148832,123
32#32Anthropicclaude-sonnet-4-6Anthropic14821478–148731,850
33#33Zglm-5.2-maxZ.ai14821477–148818,859
34#34Anthropicclaude-opus-4-5-20251101-high-32kAnthropic14821477–148814,837
35#35Anthropicclaude-opus-4-8Anthropic14821477–148728,640
36#36Ogpt-5.2-chat-latest-20260210OpenAI14811476–148715,854
37#37Zglm-5.1Z.ai14811477–148625,210
38#38xgrok-4.20-beta1xAI14811475–148712,733
39#39Xiaomimimo-v2.5-proXiaomi14801475–148429,857
40#40Anthropicclaude-opus-4-5-20251101Anthropic14791474–148331,143
41#41Googlegemini-3.5-flash-highGoogle14791473–148420,509
42#42DeepSeekdeepseek-v4-pro-high-20260813DeepSeek14791469–14883,755
43#43Baiduernie-5.1Baidu14781473–148417,926
44#44Zglm-5.3-flashZ.ai14781471–14858,546
45#45Googlegemini-3.5-flash-mediumGoogle14781472–148319,998
46#46xgrok-4.20-beta-0309-reasoningxAI14781473–148330,381
47#47Ogpt-5.4-highOpenAI14761471–148129,222
48#48Googlegemini-3-flashGoogle14761470–148212,474
49#49xgrok-4.5xAI14741468–148016,121
50#50xgrok-4.20-multi-agent-beta-0309xAI14741469–147829,508

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