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
151Qwen3 VL 235Bthinking· LMArena data1,425.6
152ERNIE-5.0-Preview1203· LMArena data1,425.3
153Qwen 3 235B A22B2507, thinking· LMArena data1,424.7
154Gemini 2.5 Flash· LMArena data1,423.4
155Grok 4.7xHigh· LMArena data1,423.3
156MiniMax-M2.1 Preview· LMArena data1,421.1
157Grok 4 FastReasoning· LMArena data1,420.3
158Hunyuan Vision 1.5 Thinking· LMArena data1,419.9
159Muse Glimmer· LMArena data1,417.9
160MiMo V2 FlashThinking· LMArena data1,417.8
161DeepSeek V3.1Thinking· LMArena data1,416.9
162Qwen3 30B A3B Instruct2507· LMArena data1,416.2
163Claude Sonnet 4Thinking 32K, 20250514· LMArena data1,414.6
164DeepSeek V3.1· LMArena data1,414
165Grok 4.3· LMArena data1,413.8
166nova-experimental-chat10-20· LMArena data1,413.5
167ChatGPT-4o Latest20250326· LMArena data1,413
168Qwen3 Coder· LMArena data1,412.6
169Qwen3.5 Flash· LMArena data1,411.9
170Grok 4.1 FastReasoning· LMArena data1,411.6
171ERNIE-5.0-Preview1022· LMArena data1,411.3
172Qwen3.5 35B A3B· LMArena data1,409.9
173Grok 40709· LMArena data1,408.5
174OpenAI o32025-04-16· LMArena data1,407.3
175DeepSeek V3.1 Terminus· LMArena data1,407.1
176GPT-5.3 Chat· LMArena data1,406.8
177GPT-5 miniHigh· LMArena data1,406.2
178GPT 5.4 NanoHigh· LMArena data1,404
179Nemotron 3 Super 120B A12B· LMArena data1,403.7
180Claude Opus 420250514· LMArena data1,401.6
181Gemini 2.5 Flash Preview09-2025· LMArena data1,400.5
182Gemini 3.1 Flash Lite· LMArena data1,400.2
183Kimi K2 Preview0905· LMArena data1,399.3
184GPT-5 Chat· LMArena data1,398.3
185Qwen 3 235B A22BNon-Thinking· LMArena data1,397.8
186GLM 4.5 Air· LMArena data1,397.3
187GPT-4.5 Preview2025-02-27· LMArena data1,396.4
188Granite 4.2 30B· LMArena data1,394
189Qwen3 Next 80B A3Bthinking· LMArena data1,391.7
190Mercury 2· LMArena data1,391.6
191GLM 4.6v· LMArena data1,391.2
192GPT 4.12025-04-14· LMArena data1,390.6
193Hunyuan T120250711· LMArena data1,389.1
194Ling Flash 2.0· LMArena data1,388.1
195Nova 2 Lite· LMArena data1,385.9
196Mistral Medium 32505· LMArena data1,385.6
197Qwen 3 235B A22B· LMArena data1,384.6
198GLM 4.7 Flash· LMArena data1,382.2
199Nemotron 3.5 Lightning 30B A3BNVFP4· LMArena data1,381.5
200Trinity Large Preview· LMArena data1,381.5

Showing 151–200 of 418 results.

Data credits: LMArena, CC BY 4.0 (licence)