Skip to content

Benchmark

WebDev Arena

Coding benchmarks compare models on programming tasks.

Models measured
106
Scores recorded
132
Sources
2
IQ weight
2.30

Score distribution

1,469.2
Mean
1,463.6
Median
142.8
Std dev
1,271.8
10th percentile
1,651.9
90th percentile
1,149
Min
1,1491,820.3
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.30 for chat models, measured over 106 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
101DeepSeek V3.2 Expthinking· Epoch AI Benchmarking Hub data1,367
102Gemma 4 31B IT· Epoch AI Benchmarking Hub data1,364.1
103Gemma 4 26B A4B· Epoch AI Benchmarking Hub data1,361.4
104GPT 5.1low· Epoch AI Benchmarking Hub data1,359
105Qwen3.5 27B· Epoch AI Benchmarking Hub data1,357.4
106Grok 4.3· Epoch AI Benchmarking Hub data1,357.2
107Laguna M.1· Epoch AI Benchmarking Hub data1,347.5
108GPT 5.1· Epoch AI Benchmarking Hub data1,340.9
109GLM 4.6· Epoch AI Benchmarking Hub data1,340.6
110GPT-5.2 Codex· Epoch AI Benchmarking Hub data1,338.7
111Kimi K2 Thinking· Epoch AI Benchmarking Hub data1,337
112GPT-5.1 Codex· Epoch AI Benchmarking Hub data1,336.3
113MiMo V2 Flash· Epoch AI Benchmarking Hub data1,330.6
114Claude Haiku 4.5· Epoch AI Benchmarking Hub data1,329.3
115DeepSeek V3.2· Epoch AI Benchmarking Hub data1,324.7
116Laguna XS.2· Epoch AI Benchmarking Hub data1,302.4
117MiniMax M2· Epoch AI Benchmarking Hub data1,297.8
118Qwen3 Coder· Epoch AI Benchmarking Hub data1,273.8
119DeepSeek V3.2 Exp· Epoch AI Benchmarking Hub data1,271.8
120Mistral Medium2604· Epoch AI Benchmarking Hub data1,264.9
121Gemini 3.1 Flash Lite· Epoch AI Benchmarking Hub data1,254.3
122Qwen3.6 35B A3B· Epoch AI Benchmarking Hub data1,250.2
123GPT-5.1 Codex Mini· Epoch AI Benchmarking Hub data1,247
124Qwen3.5 Flash· Epoch AI Benchmarking Hub data1,238.2
125Trinity Large Thinking· Epoch AI Benchmarking Hub data1,236.6
126Mistral Large 3· Epoch AI Benchmarking Hub data1,229.5
127Gemini 2.5 Pro· Epoch AI Benchmarking Hub data1,225.7
128Grok 4.1 Fastreasoning· Epoch AI Benchmarking Hub data1,223
129Grok 4.1· Epoch AI Benchmarking Hub data1,211
130Mercury 2· Epoch AI Benchmarking Hub data1,166.6
131Grok Code Fast 1· Epoch AI Benchmarking Hub data1,165.1
132Grok 4 Fast· Epoch AI Benchmarking Hub data1,149

Showing 101–132 of 132 results.

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Data by LLM Stats