Skip to content

Benchmark

Arena ELO - English

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

Models measured
366
Scores recorded
423
Sources
1
IQ weight
1.26

Score distribution

1,327.7
Mean
1,373.1
Median
138.5
Std dev
1,119.5
10th percentile
1,468.7
90th percentile
845.9
Min
845.91,532
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.26 for chat models, measured over 366 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
201Mercury 2· LMArena data1,378.7
202Kimi K2 Preview0905· LMArena data1,378.6
203Qwen 3 235B A22B· LMArena data1,377.7
204Nemotron 3 Nano 30B A3BBF16· LMArena data1,376.9
205Gemma 3 27B IT· LMArena data1,376.6
206Kimi K2 Preview0711· LMArena data1,376.5
207Grok 3 Minibeta· LMArena data1,376.3
208Claude Opus 420250514· LMArena data1,375.7
209Qwen2.5-Max· LMArena data1,375.6
210GPT OSS 120B· LMArena data1,374.7
211Step3· LMArena data1,373.1
212Gemini 2.5 Flash-Lite PreviewThinking, 06-17· LMArena data1,372.9
213GLM 4.7 Flash· LMArena data1,372.6
214o12024-12-17· LMArena data1,372.2
215o4 Mini2025-04-16· LMArena data1,367.4
216Ring Flash 2.0· LMArena data1,367.2
217Nemotron 3.5 Lightning 30B A3BNVFP4· LMArena data1,366.7
218Gemini 2.0 Flash001· LMArena data1,365.6
219MiniMax M2· LMArena data1,364.7
220Claude Sonnet 4Thinking 32K, 20250514· LMArena data1,364.4
221MiniMax M1· LMArena data1,362.9
222GLM 4.5V· LMArena data1,362.2
223Qwen3 Coder· LMArena data1,359.6
224Llama 3.3 Nemotron Super 49B v1.5· LMArena data1,359.5
225Qwen3 32B· LMArena data1,359.1
226Trinity Large Preview· LMArena data1,358.1
227Mistral Small 3.22506· LMArena data1,357.8
228GPT-4.1 mini2025-04-14· LMArena data1,355.8
229Trinity Large Thinking· LMArena data1,355.3
230Llama 3.3 Nemotron Super 49B v1· LMArena data1,353.8
231Olmo 3.1 32B Instruct· LMArena data1,353.4
232Step-1o Turbo202506· LMArena data1,352.8
233o3 MiniHigh· LMArena data1,351.1
234QwQ 32B· LMArena data1,350.8
235Gemma 3 12B IT· LMArena data1,348.5
236Olmo 3 32B Think· LMArena data1,348.2
237DeepSeek V3· LMArena data1,345.8
238Llama 3.1 Nemotron Ultra 253B v1· LMArena data1,345
239Step-2 16K Exp202412· LMArena data1,344.4
240Olmo 3.1 32B Think· LMArena data1,344.3
241Claude Sonnet 420250514· LMArena data1,344
242Command A03-2025· LMArena data1,343.5
243GLM 4 Plus0111· LMArena data1,340.3
244O1 Mini· LMArena data1,340.1
245Qwen Plus0125· LMArena data1,338.6
246Granite 4.2 8B· LMArena data1,336.1
247Qwen3 30B A3B· LMArena data1,334.6
248Hunyuan TurboS20250226· LMArena data1,334
249o3 Mini· LMArena data1,333.2
250Gemini 2.0 Flash-Lite Preview02-05· LMArena data1,333.1

Showing 201–250 of 423 results.

Data credits: LMArena, CC BY 4.0 (licence)