Valumigo

LMArena · German

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 German in LMArena text conversations.

How to read the score: Shows which models voters preferred for questions in German. 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-3-pro and 2nd-place glm-5.3-max overlap. This aggregation alone does not clearly establish their order.
  • 32 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 4.
  • The 1st-place model received 805 votes, and this leaderboard includes 307 models.

German LMArena

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

144014701500153015601590
Googlegemini-3-pro
1522
Zglm-5.3-max
1520
Metamuse-spark-1.3-max
1519
Metamuse-spark
1511
Anthropicclaude-opus-4-6-high
1510
Anthropicclaude-opus-5-max
1506
Anthropicclaude-opus-4-7-high
1505
Anthropicclaude-fable-5-high
1503
Ogpt-5.6-sol-xhigh
1501
Googlegemini-3-flash
1499
Googlegemini-3.1-pro-preview
1495
Moonshot AIkimi-k3-max
1492
Googlegemini-3.5-flash-medium
1492
Anthropicclaude-opus-4-8-high
1491
Ogpt-5.5
1490
Alibabaqwen3.8-max
1490
xgrok-4.20-beta1
1489
Anthropicclaude-fable-5.1-max
1487
Googlegemini-3.7-flash-high
1487
Ogpt-5.6-terra-xhigh
1482

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-3-pro#1
  • ZZ.aiglm-5.3-max#2
  • MetaMetamuse-spark-1.3-max#3
  • AnthropicAnthropicclaude-opus-4-6-high#5
  • OOpenAIgpt-5.6-sol-xhigh#9
  • Moonshot AIMoonshot AIkimi-k3-max#13
  • AlibabaAlibabaqwen3.8-max#17
  • xxAIgrok-4.20-beta1#19
  • BaiduBaiduernie-5.1#38
View table (top 50)
RankModelDeveloperScore95% confidence intervalVotes
1#1Googlegemini-3-proGoogle15221500–1545805
2#2Zglm-5.3-maxZ.ai15201486–1554282
3#3Metamuse-spark-1.3-maxMeta15191477–1562182
4#4Metamuse-sparkMeta15111471–1551237
5#5Anthropicclaude-opus-4-6-highAnthropic15101492–15271,251
6#6Anthropicclaude-opus-5-maxAnthropic15061478–1534489
7#7Anthropicclaude-opus-4-7-highAnthropic15051486–15241,014
8#8Anthropicclaude-fable-5-highAnthropic15031478–1528586
9#9Ogpt-5.6-sol-xhighOpenAI15011476–1526566
10#10Googlegemini-3-flashGoogle14991474–1524572
11#11Anthropicclaude-opus-4-7Anthropic14971477–15161,035
12#12Googlegemini-3.1-pro-previewGoogle14951480–15102,025
13#13Moonshot AIkimi-k3-maxMoonshot AI14921466–1518547
14#14Googlegemini-3.5-flash-mediumGoogle14921469–1514741
15#15Anthropicclaude-opus-4-8-highAnthropic14911472–15101,061
16#16Ogpt-5.5OpenAI14901471–15091,105
17#17Alibabaqwen3.8-maxAlibaba14901460–1519362
18#18Anthropicclaude-opus-4-6Anthropic14901472–15071,277
19#19xgrok-4.20-beta1xAI14891461–1517442
20#20Anthropicclaude-fable-5.1-maxAnthropic14871448–1527220
21#21Googlegemini-3.7-flash-highGoogle14871454–1520313
22#22Anthropicclaude-opus-5-highAnthropic14871466–1508917
23#23Googlegemini-3.5-flash-highGoogle14831460–1505762
24#24Ogpt-5.6-terra-xhighOpenAI14821458–1507592
25#25Ogpt-5.2-chat-latest-20260210OpenAI14811456–1506564
26#26Googlegemini-3.6-flash-highGoogle14791454–1504571
27#27Anthropicclaude-opus-4-5-20251101Anthropic14781460–14971,129
28#28Ogpt-4.5-preview-2025-02-27OpenAI14771445–1509319
29#29Googlegemini-3-flash (thinking-minimal)Google14771460–14931,464
30#30Anthropicclaude-opus-4-5-20251101-high-32kAnthropic14771453–1500662
31#31Metamuse-spark-1.1Meta14761453–1500687
32#32Ogpt-5.6-luna-xhighOpenAI14761452–1500655
33#33Ogpt-5.4-highOpenAI14761457–14951,088
34#34xgrok-4.20-multi-agent-beta-0309xAI14751456–14951,046
35#35Zglm-5.2-maxZ.ai14731451–1494805
36#36Alibabaqwen3.5-max-previewAlibaba14721442–1502382
37#37Googlegemini-3.5-flash-liteGoogle14721448–1495637
38#38Baiduernie-5.1Baidu14721449–1494749
39#39Anthropicclaude-opus-4-8Anthropic14721453–14901,082
40#40Googlegemini-3.8-flash-highGoogle14721443–1500398
41#41Ogpt-5.5-highOpenAI14711452–14901,050
42#42Googlegemini-2.5-proGoogle14701457–14832,638
43#43DeepSeekdeepseek-v4-proDeepSeek14681449–1488999
44#44Anthropicclaude-sonnet-5-highAnthropic14681445–1491719
45#45Alibabaqwen3.7-plusAlibaba14661444–1488760
46#46xgrok-4.1xAI14661448–14841,248
47#47Ogpt-5.5-instantOpenAI14651436–1494427
48#48Zglm-5.3-flashZ.ai14651435–1494395
49#49Xiaomimimo-v2.5-proXiaomi14641445–14821,198
50#50Zglm-5.1Z.ai14641444–1484928

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