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
51GPT-5.6 LunaxHigh· LMArena data1,455.9
52DeepSeek V4.1 Flash 0910Max· LMArena data1,455.6
53Claude Sonnet 5.5xHigh· LMArena data1,454.4
54Kimi K2.6· LMArena data1,453.7
55Step 5 Preview· LMArena data1,453.1
56Qwen3.6 Plus· LMArena data1,452.9
57Gemini 3.5 Flash Lite· LMArena data1,452.8
58Claude Opus 4.520251101· LMArena data1,449.1
59GPT-5.2 Chat20260210· LMArena data1,448.4
60DeepSeek-V4-Pro PreviewHigh· LMArena data1,448.2
61Claude Opus 4.8· LMArena data1,448.1
62Grok 4.5· LMArena data1,448
63GPT-6.1 SolMax· LMArena data1,447.7
64GLM 5· LMArena data1,447.7
65GLM 4.6· LMArena data1,446.9
66Grok 4.1· LMArena data1,445.8
67MiMo V2.6 Flash· LMArena data1,443.2
68GPT 5.2High· LMArena data1,442
69Qwen3.5 397B A17B· LMArena data1,441.9
70Doubao Seed 2.0 Pro· LMArena data1,441.6
71Grok 4.20Reasoning, 0309, beta· LMArena data1,441.3
72Hy3 (Deep Infra)· LMArena data1,440.9
73Kimi K2.5Thinking· LMArena data1,440.7
74Claude Sonnet 5High· LMArena data1,440.7
75DeepSeek V3.2 Exp· LMArena data1,439.8
76Claude Opus 4.5High, 32K, 20251101· LMArena data1,439.8
77GPT 5.4· LMArena data1,439.4
78Grok 4.1Thinking· LMArena data1,438.9
79Inkling FP4· LMArena data1,438.5
80Mistral Large 3· LMArena data1,438.4
81GPT 5.1High· LMArena data1,438
82Qwen3 Max2025-09-23· LMArena data1,437.1
83DeepSeek V3.2 ExpThinking· LMArena data1,437
84Qwen 3.8 27B· LMArena data1,436.9
85ERNIE 5.00110· LMArena data1,435.6
86Mistral Medium 3.12508· LMArena data1,434
87Qwen3 235B A22B Instruct 25072507· LMArena data1,432.1
88Grok 3 Preview02-24· LMArena data1,431.3
89GPT 5.2· LMArena data1,429.2
90Gemini 3.1 Flash Lite· LMArena data1,428.9
91Claude Sonnet 4.6· LMArena data1,428.7
92Grok 40709· LMArena data1,428.3
93Claude Haiku 5.5High· LMArena data1,427.1
94Claude Sonnet 4.5High, 32K, 20250929· LMArena data1,426.6
95GLM 4.7· LMArena data1,426
96MiniMax M3· LMArena data1,425.7
97Qwen3 VL 235B· LMArena data1,424
98Qwen3.5 122B-A10B· LMArena data1,423.4
99ChatGPT-4o Latest20250326· LMArena data1,423.2
100Claude Sonnet 4.520250929· LMArena data1,422.1

Showing 51–100 of 319 results.

Data credits: LMArena, CC BY 4.0 (licence)