Skip to content

Benchmark

Arena ELO Style-Controlled

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

Models measured
366
Scores recorded
423
Sources
1
IQ weight
1.10

Score distribution

1,341.3
Mean
1,363.7
Median
121
Std dev
1,152.6
10th percentile
1,474.5
90th percentile
953.4
Min
953.41,527
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.10 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
201Gemini 2.5 Flash-Lite PreviewThinking, 06-17· LMArena data1,374.9
202Qwen 3 235B A22B· LMArena data1,374.8
203Claude 3.5 Sonnet20241022· LMArena data1,374.4
204Qwen2.5-Max· LMArena data1,373.7
205GLM 4.5 Air· LMArena data1,372.9
206Claude Sonnet 3.720250219· LMArena data1,372.4
207Qwen3 Next 80B A3Bthinking· LMArena data1,369.6
208Trinity Large Thinking· LMArena data1,367.1
209Gemma 3 27B IT· LMArena data1,365.4
210GLM 4.7 Flash· LMArena data1,364.6
211MiniMax M1· LMArena data1,363.7
212Grok 3 MiniHigh· LMArena data1,363.6
213o3 MiniHigh· LMArena data1,363.6
214nova-experimental-chat11-10· LMArena data1,363.3
215Gemini 2.0 Flash001· LMArena data1,360.2
216Nemotron 3 Super 120B A12B· LMArena data1,359.9
217DeepSeek V3· LMArena data1,358.4
218Grok 3 Minibeta· LMArena data1,358.1
219Mistral Small 3.22506· LMArena data1,356.5
220INTELLECT-3· LMArena data1,355.8
221Gemini 2.0 Flash-Lite Preview02-05· LMArena data1,353.6
222Command A03-2025· LMArena data1,353.6
223GLM 4.5V· LMArena data1,352
224Nemotron 3.5 Lightning 30B A3BNVFP4· LMArena data1,351.6
225GPT OSS 120B· LMArena data1,351.6
226Gemini 1.5 Pro002· LMArena data1,351.4
227Step3· LMArena data1,348.9
228Hunyuan TurboS20250226· LMArena data1,348.8
229o3 Mini· LMArena data1,348.2
230nova-experimental-chat10-20· LMArena data1,347.9
231Llama 3.1 Nemotron Ultra 253B v1· LMArena data1,347.6
232Qwen3 32B· LMArena data1,346.8
233nova-experimental-chat10-09· LMArena data1,346.2
234GPT 4o2024-05-13· LMArena data1,346.2
235Qwen Plus0125· LMArena data1,345.9
236MiniMax M2· LMArena data1,343.5
237Claude 3.5 Sonnet20240620· LMArena data1,343.4
238Llama 3.3 Nemotron Super 49B v1.5· LMArena data1,343.1
239Ling Flash 2.0· LMArena data1,343.1
240Mercury 2· LMArena data1,343.1
241GLM 4 Plus0111· LMArena data1,342.8
242Gemma 3 12B IT· LMArena data1,341.8
243Hunyuan Turbo0110· LMArena data1,340.7
244Granite 4.2 30B· LMArena data1,339.7
245GPT-5 nanoHigh· LMArena data1,337.8
246O1 Mini· LMArena data1,336.8
247Gemini Advanced0514· LMArena data1,336.1
248Grok 22024-08-13· LMArena data1,335.7
249GPT 4o2024-08-06· LMArena data1,335.7
250Llama 3.1 405B InstructBF16· LMArena data1,335.5

Showing 201–250 of 423 results.

Data credits: LMArena, CC BY 4.0 (licence)