Skip to content

Benchmark

Arena ELO - Non English

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

Models measured
366
Scores recorded
423
Sources
1
IQ weight
1.20

Score distribution

1,288.7
Mean
1,334.4
Median
160.8
Std dev
1,032.5
10th percentile
1,449.6
90th percentile
781.3
Min
781.31,534.5
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.20 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
201Qwen 3 235B A22B· LMArena data1,348.4
202Qwen3 Coder· LMArena data1,345.5
203Qwen3 Next 80B A3Bthinking· LMArena data1,342.8
204Gemini 2.0 Flash001· LMArena data1,342.2
205nova-experimental-chat10-09· LMArena data1,339.9
206Granite 4.2 30B· LMArena data1,339.5
207MiniMax M2.5· LMArena data1,338.2
208Nova 2 Lite· LMArena data1,337.1
209o4 Mini2025-04-16· LMArena data1,336.3
210Ling Flash 2.0· LMArena data1,335
211Gemma 3 27B IT· LMArena data1,334.4
212Claude Sonnet 4Thinking 32K, 20250514· LMArena data1,332.7
213Mercury 2· LMArena data1,330.9
214GLM 4.7 Flash· LMArena data1,330.6
215Claude Sonnet 420250514· LMArena data1,330
216INTELLECT-3· LMArena data1,328.8
217Step3· LMArena data1,327.1
218Trinity Large Thinking· LMArena data1,325.5
219Gemini 2.0 Flash-Lite Preview02-05· LMArena data1,322.6
220Nemotron 3 Nano 30B A3BBF16· LMArena data1,320.3
221MiniMax M1· LMArena data1,319.5
222Trinity Large Preview· LMArena data1,318.8
223o3 MiniHigh· LMArena data1,318.7
224GPT-4.1 mini2025-04-14· LMArena data1,317.9
225Gemma 3 12B IT· LMArena data1,317.9
226Qwen3 32B· LMArena data1,316.7
227DeepSeek V3· LMArena data1,315.5
228Llama 3.3 Nemotron Super 49B v1.5· LMArena data1,315.4
229Mistral Small 3.22506· LMArena data1,315.1
230O1 Preview· LMArena data1,315
231GLM 4 Plus0111· LMArena data1,313.8
232GPT-5 nanoHigh· LMArena data1,312.9
233Command A03-2025· LMArena data1,312.9
234MiniMax M2· LMArena data1,312.7
235Step-1o Turbo202506· LMArena data1,312.6
236Gemini 1.5 Pro002· LMArena data1,312
237Qwen Plus0125· LMArena data1,309.6
238QwQ 32B· LMArena data1,305.3
239GLM 4.5V· LMArena data1,303.1
240Granite 4.2 8B· LMArena data1,300.4
241o3 Mini· LMArena data1,299.7
242Ring Flash 2.0· LMArena data1,299.5
243Hunyuan TurboS20250226· LMArena data1,297.9
244Nemotron 3.5 Lightning 30B A3BNVFP4· LMArena data1,297.1
245Claude Sonnet 3.7Thinking 32K, 20250219· LMArena data1,296.1
246Qwen3 30B A3B· LMArena data1,295
247Step-2 16K Exp202412· LMArena data1,290
248O1 Mini· LMArena data1,288.5
249Claude Sonnet 3.720250219· LMArena data1,286.2
250Gemma 3n E4B IT· LMArena data1,285

Showing 201–250 of 423 results.

Data credits: LMArena, CC BY 4.0 (licence)