Skip to content

Benchmark

Arena ELO - German

People compare model answers and choose which they prefer. Higher scores are better.

Models measured
273
Scores recorded
319
Sources
1
IQ weight
1.52

Score distribution

1,328.6
Mean
1,372.1
Median
138.3
Std dev
1,110.8
10th percentile
1,469.8
90th percentile
901.9
Min
901.91,585.2
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.52 for chat models, measured over 273 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Gemini 4 ArgonHigh· LMArena data1,585.2
2Claude Opus 5.5High· LMArena data1,525
3Claude Opus 5Max· LMArena data1,519.3
4Gemini 3 Pro Preview· LMArena data1,515.8
5Gemini 3.7 FlashHigh· LMArena data1,514.1
6Muse WonderMax· LMArena data1,508.4
7Muse Spark 1.3Max· LMArena data1,507.7
8Gemini 3.8 FlashHigh· LMArena data1,506.4
9Claude Fable 5.1Max· LMArena data1,505.5
10Claude Opus 5High· LMArena data1,502.3
11Claude Opus 4.6High· LMArena data1,501.4
12GLM 5.3Max· LMArena data1,499.1
13Muse Spark· LMArena data1,499
14Gemini 3 Flash· LMArena data1,496.7
15Claude Opus 4.7High· LMArena data1,495.7
16Gemini 3.1 Pro Preview· LMArena data1,491.3
17Gemini 3.5 FlashHigh· LMArena data1,491.1
18Gemini 3.5 FlashMedium· LMArena data1,490.2
19Claude Opus 4.6· LMArena data1,489
20Qwen3.5-Max-Preview· LMArena data1,486.7
21Gemini 2.5 Pro· LMArena data1,486.7
22Claude Opus 4.7· LMArena data1,485.7
23Kimi K3Max· LMArena data1,482.8
24Gemini 3.6 FlashHigh· LMArena data1,482
25Claude Fable 5High· LMArena data1,481.9
26GPT 5.5· LMArena data1,480.9
27Muse Spark 1.2xHigh· LMArena data1,477.1
28Qwen3.8 Max· LMArena data1,473.6
29Nemotron 3 UltraNVFP4· LMArena data1,472.7
30GPT 5.4High· LMArena data1,472.2
31GPT-5.6 SolxHigh· LMArena data1,472.1
32ERNIE 5.1· LMArena data1,471.3
33Muse Spark 1.1· LMArena data1,469.8
34Claude Opus 4.8High· LMArena data1,469.3
35Qwen3.7 Plus· LMArena data1,468
36GLM 5.2Max· LMArena data1,466.9
37Gemini 3 FlashMinimal· LMArena data1,466.4
38GLM 5.1· LMArena data1,466.1
39Qwen3 Max Preview· LMArena data1,464.8
40Grok 4.20 Beta 1· LMArena data1,463.5
41GPT-5.6 TerraxHigh· LMArena data1,462.8
42GPT-6 AstraMax· LMArena data1,462.5
43ERNIE-5.0-Preview1203· LMArena data1,460.3
44Mistral Medium 3.5· LMArena data1,459.7
45GPT 5.5High· LMArena data1,459.1
46MiMo V2.5 Pro· LMArena data1,457.1
47DeepSeek V4 Pro· LMArena data1,456.7
48GPT-4.5 Preview2025-02-27· LMArena data1,456.6
49GLM 5.3 Flash· LMArena data1,456.5
50Grok 4.20 Multi-Agent0309, beta· LMArena data1,456.3

Showing 1–50 of 319 results.

Data credits: LMArena, CC BY 4.0 (licence)