Skip to content

Benchmark

Arena ELO - Industry Writing and Literature and Language

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

Models measured
365
Scores recorded
422
Sources
1
IQ weight
1.17

Score distribution

1,297.8
Mean
1,328.7
Median
142.8
Std dev
1,086
10th percentile
1,453.9
90th percentile
809.1
Min
809.11,540.8
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.17 for chat models, measured over 365 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
201O1 Preview· LMArena data1,339.5
202Qwen3 Coder· LMArena data1,339.4
203Claude Sonnet 3.7Thinking 32K, 20250219· LMArena data1,337.8
204GPT 5.4 NanoHigh· LMArena data1,337.2
205Qwen3 30B A3B Instruct2507· LMArena data1,335.9
206INTELLECT-3· LMArena data1,335.9
207Qwen 3 235B A22B· LMArena data1,335.9
208DeepSeek V3· LMArena data1,331.2
209Qwen3 Next 80B A3Bthinking· LMArena data1,331.1
210Nemotron 3 Super 120B A12B· LMArena data1,330.8
211Trinity Large Preview· LMArena data1,328.7
212Kimi K2 Preview0711· LMArena data1,328.5
213Command A03-2025· LMArena data1,327.5
214GLM 4 Plus0111· LMArena data1,326.4
215Gemini 1.5 Pro002· LMArena data1,326.3
216Step3· LMArena data1,326.2
217Claude Sonnet 3.720250219· LMArena data1,324
218Gemini 2.0 Flash-Lite Preview02-05· LMArena data1,321.5
219nova-experimental-chat10-09· LMArena data1,320.4
220GLM 4.7 Flash· LMArena data1,319.2
221GPT-4.1 mini2025-04-14· LMArena data1,318.3
222Nova 2 Lite· LMArena data1,317.9
223Trinity Large Thinking· LMArena data1,317.3
224o4 Mini2025-04-16· LMArena data1,315.4
225Claude 3.5 Sonnet20241022· LMArena data1,313.8
226o3 MiniHigh· LMArena data1,313.2
227MiniMax M1· LMArena data1,310.7
228Mistral Small 3.22506· LMArena data1,310
229Step-1o Turbo202506· LMArena data1,309.4
230Granite 4.2 30B· LMArena data1,307.8
231Gemma 3 12B IT· LMArena data1,307
232GPT OSS 120B· LMArena data1,305.4
233Step-2 16K Exp202412· LMArena data1,303.5
234GLM 4.5V· LMArena data1,302.1
235Hunyuan TurboS20250226· LMArena data1,301.9
236Mercury 2· LMArena data1,301.5
237QwQ 32B· LMArena data1,301
238Llama 3.3 Nemotron Super 49B v1· LMArena data1,300.5
239Llama 3.1 Nemotron Ultra 253B v1· LMArena data1,300.2
240Qwen3 32B· LMArena data1,298.2
241GPT 4o2024-05-13· LMArena data1,297.8
242Ring Flash 2.0· LMArena data1,296.2
243Qwen Plus0125· LMArena data1,296
244Ling Flash 2.0· LMArena data1,295.4
245MiniMax M2· LMArena data1,294.9
246o3 Mini· LMArena data1,294.7
247Gemini 1.5 Flash002· LMArena data1,293.4
248Llama 3.3 Nemotron Super 49B v1.5· LMArena data1,293.2
249Grok 22024-08-13· LMArena data1,291.9
250Hunyuan Turbo0110· LMArena data1,290.6

Showing 201–250 of 422 results.

Data credits: LMArena, CC BY 4.0 (licence)