WebCoderBench - Functionality Correctness — leaderboard

Metric: Score (%). Source: huggingface.co. 11 models tracked.

Top models

#ModelScore
1GPT-5 (High)79.18
2GPT-5 Codex (High)74.82
3MiniMax-M272.52
4Gemini 2.5 Pro68.28
5GLM-4.557.73
6DeepSeek V3.1 Terminus56.25
7Qwen 3 Coder Plus54.95
8DeepSeek R1 052854.67
9DeepSeek V3.1 (Thinking)54.03
10DeepSeek V3.153.68
11GPT-4o (2024-11-20)49.42

Interactive version: aibenchmarks.dev/benchmark?slug=webcoderbench-functionality-correctness · How the rankings work · Data refreshed daily, snapshot 2026-07-12.