Skip to content

Benchmark

Arena ELO - Coding

Coding benchmarks compare models on programming tasks. Higher scores are better.

Models measured
361
Scores recorded
418
Sources
1
IQ weight
1.28

Score distribution

1,325
Mean
1,374.5
Median
162.1
Std dev
1,081.6
10th percentile
1,488
90th percentile
682.8
Min
682.81,564.3
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.28 for chat models, measured over 361 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
201MiniMax M2.5· LMArena data1,380.6
202GPT OSS 120B· LMArena data1,379.4
203Claude Sonnet 420250514· LMArena data1,379.3
204Grok 3 MiniHigh· LMArena data1,379.1
205Nemotron 3 Nano 30B A3BBF16· LMArena data1,378.6
206o3 MiniHigh· LMArena data1,378.1
207Kimi K2 Preview0711· LMArena data1,376.8
208Granite 4.2 8B· LMArena data1,375
209INTELLECT-3· LMArena data1,374.5
210Gemini 2.5 Flash-Lite PreviewThinking, 06-17· LMArena data1,372.8
211Gemini 2.5 Flash-Lite PreviewNon-Thinking, 09-2025· LMArena data1,371.7
212DeepSeek R1· LMArena data1,371.3
213MiniMax M2· LMArena data1,370.6
214nova-experimental-chat10-09· LMArena data1,369.8
215o4 Mini2025-04-16· LMArena data1,368.1
216DeepSeek V30324· LMArena data1,367.9
217GPT-4.1 mini2025-04-14· LMArena data1,367.2
218o12024-12-17· LMArena data1,366.8
219Grok 3 Minibeta· LMArena data1,366.7
220Step3· LMArena data1,366.6
221O1 Preview· LMArena data1,366.6
222Ring Flash 2.0· LMArena data1,366.2
223o3 Mini· LMArena data1,362.9
224Mistral Small 3.22506· LMArena data1,362.5
225O1 Mini· LMArena data1,362.2
226Hunyuan TurboS20250416· LMArena data1,361.4
227Claude Sonnet 3.7Thinking 32K, 20250219· LMArena data1,360.5
228Granite 4.2 3B· LMArena data1,359.2
229Qwen2.5-Max· LMArena data1,359.1
230MiniMax M1· LMArena data1,358.7
231Qwen3 32B· LMArena data1,357.5
232Trinity Large Thinking· LMArena data1,356.9
233Llama 3.3 Nemotron Super 49B v1.5· LMArena data1,356
234GPT-5 nanoHigh· LMArena data1,351.6
235Gemini 2.0 Flash001· LMArena data1,350.3
236GLM 4.5V· LMArena data1,347.4
237Olmo 3.1 32B Instruct· LMArena data1,346.7
238Hunyuan TurboS20250226· LMArena data1,342.5
239Claude 3.5 Sonnet20241022· LMArena data1,342.5
240Step-1o Turbo202506· LMArena data1,339.3
241Claude Sonnet 3.720250219· LMArena data1,339
242Qwen3 30B A3B· LMArena data1,336.9
243QwQ 32B· LMArena data1,332.8
244Command A03-2025· LMArena data1,330
245Qwen Plus0125· LMArena data1,328
246DeepSeek V3· LMArena data1,324.9
247Mercury· LMArena data1,322.3
248Gemma 3 27B IT· LMArena data1,322.1
249Gemini 2.0 Flash-Lite Preview02-05· LMArena data1,321.9
250Hunyuan Turbo0110· LMArena data1,319.3

Showing 201–250 of 418 results.

Data credits: LMArena, CC BY 4.0 (licence)