Skip to content

Benchmark

Arena ELO - Industry Life and Physical and Social Science

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

Models measured
364
Scores recorded
421
Sources
1
IQ weight
1.24

Score distribution

1,316.4
Mean
1,364.4
Median
158.9
Std dev
1,071.5
10th percentile
1,475.1
90th percentile
800.9
Min
800.91,549.3
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.24 for chat models, measured over 364 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
201Gemini 2.5 Flash-Lite PreviewThinking, 06-17· LMArena data1,373.2
202Qwen 3 235B A22B· LMArena data1,372.1
203Qwen3 32B· LMArena data1,372.1
204GPT-5 miniHigh· LMArena data1,370.1
205MiniMax M2.5· LMArena data1,369.4
206o12024-12-17· LMArena data1,368.8
207Llama 3.3 Nemotron Super 49B v1.5· LMArena data1,367.5
208Claude Opus 4Thinking 16K, 20250514· LMArena data1,367.1
209Gemma 3 12B IT· LMArena data1,365.8
210Kimi K2 Preview0711· LMArena data1,364.4
211Claude Opus 420250514· LMArena data1,362.6
212INTELLECT-3· LMArena data1,361.2
213Gemini 2.0 Flash001· LMArena data1,360.6
214GLM 4.7 Flash· LMArena data1,359.4
215Step-1o Turbo202506· LMArena data1,358.3
216Trinity Large Thinking· LMArena data1,354.2
217MiniMax M1· LMArena data1,353.7
218o4 Mini2025-04-16· LMArena data1,353.6
219Step3· LMArena data1,353.5
220Qwen Plus0125· LMArena data1,352.5
221Trinity Large Preview· LMArena data1,352.3
222Nemotron 3 Nano 30B A3BBF16· LMArena data1,352.2
223GLM 4 Plus0111· LMArena data1,350.4
224MiniMax M2· LMArena data1,349
225O1 Preview· LMArena data1,348.3
226Qwen3 Coder· LMArena data1,347
227QwQ 32B· LMArena data1,346.7
228Claude Sonnet 4Thinking 32K, 20250514· LMArena data1,345.3
229Ring Flash 2.0· LMArena data1,342.3
230Mercury 2· LMArena data1,342.1
231Claude Sonnet 420250514· LMArena data1,339.9
232o3 MiniHigh· LMArena data1,339.2
233Mistral Small 3.22506· LMArena data1,339.1
234Command A03-2025· LMArena data1,339
235DeepSeek V3· LMArena data1,332.6
236Llama 3.3 Nemotron Super 49B v1· LMArena data1,332.5
237Granite 4.2 8B· LMArena data1,332
238Gemini 2.0 Flash-Lite Preview02-05· LMArena data1,331.6
239GLM 4.5V· LMArena data1,330.2
240Step-2 16K Exp202412· LMArena data1,330
241GPT-4.1 mini2025-04-14· LMArena data1,328.4
242Hunyuan Turbo0110· LMArena data1,327.7
243Nemotron 3.5 Lightning 30B A3BNVFP4· LMArena data1,326.7
244Llama 3.1 Nemotron Ultra 253B v1· LMArena data1,324
245Gemma 3n E4B IT· LMArena data1,323.4
246Qwen3 30B A3B· LMArena data1,321.3
247Gemini 1.5 Pro002· LMArena data1,320.6
248GPT-5 nanoHigh· LMArena data1,318.2
249Hunyuan TurboS20250226· LMArena data1,317.8
250Qwen2.5-Plus1127· LMArena data1,317.3

Showing 201–250 of 421 results.

Data credits: LMArena, CC BY 4.0 (licence)