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
101MiniMax M2.7· LMArena data1,453.5
102Kimi K2 Thinking· LMArena data1,453.4
103Claude Haiku 4.520251001· LMArena data1,453.4
104GPT 5.1High· LMArena data1,453.2
105DeepSeek-V4-Pro PreviewHigh· LMArena data1,452.9
106Claude Haiku 5.5High· LMArena data1,451.8
107Inkling Small· LMArena data1,451.6
108Gemini 2.5 Pro· LMArena data1,451.5
109GPT-6.2 AstraMax· LMArena data1,450.1
110Mistral Large 3· LMArena data1,449.1
111DeepSeek V3.2· LMArena data1,449
112GLM 4.6· LMArena data1,448.9
113GPT-6 SolMax· LMArena data1,447.6
114Gemma 4 26B A4B· LMArena data1,446.9
115Grok 4.20 Beta 1· LMArena data1,446.7
116nova-experimental-chat26-01-10· LMArena data1,446.5
117GPT-5.2 Chat20260210· LMArena data1,446.4
118Grok 4.1Thinking· LMArena data1,445.1
119Qwen3 235B A22B Instruct 25072507· LMArena data1,444.9
120Grok 4.1· LMArena data1,443.9
121MiMo V2 FlashNon-Thinking· LMArena data1,442.9
122Claude Opus 4Thinking 16K, 20250514· LMArena data1,442.1
123GPT 5.2High· LMArena data1,441.5
124Qwen3 Next 80B A3B Instruct· LMArena data1,440.5
125DeepSeek-V4-Flash PreviewHigh· LMArena data1,440.4
126GPT-6.2 SolMax· LMArena data1,439.8
127DeepSeek V3.2 ExpThinking· LMArena data1,438.9
128Qwen3 Max2025-09-23· LMArena data1,438.8
129Qwen3 VL 235B· LMArena data1,438.7
130GPT-5.4 miniHigh· LMArena data1,438.5
131GPT 5.1· LMArena data1,437.3
132Solar Pro 4· LMArena data1,436.7
133GPT 5High· LMArena data1,436.3
134Gemini 3 FlashMinimal· LMArena data1,436
135Qwen3.5 122B-A10B· LMArena data1,435.8
136DeepSeek V3.2 Exp· LMArena data1,435.3
137Step 3.5 Flash· LMArena data1,435.3
138GLM 4.5· LMArena data1,434.3
139GPT-6 LunaMax· LMArena data1,433.8
140Mistral Medium 3.12508· LMArena data1,433.4
141GPT-5.5 Instant· LMArena data1,433.3
142NVIDIA Nemotron 3.5 Super VL 120BNVFP4· LMArena data1,433
143nova-experimental-chat11-10· LMArena data1,432.8
144nova-experimental-chat12-10· LMArena data1,432.3
145Grok 3 Preview02-24· LMArena data1,432.2
146GPT 5.2· LMArena data1,431.7
147Grok 4 FastNon-Reasoning· LMArena data1,429
148DeepSeek R10528· LMArena data1,426.8
149Qwen3.5 27B· LMArena data1,426.5
150DeepSeek V3.1 TerminusThinking· LMArena data1,425.9

Showing 101–150 of 418 results.

Data credits: LMArena, CC BY 4.0 (licence)