WebCoderBench - Functional Alignment — leaderboard

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

Top models

#ModelScore
1GPT-5 (High)96.94
2MiniMax-M293.62
3GPT-5 Codex (High)92.04
4GLM-4.591.29
5Gemini 2.5 Pro90.33
6DeepSeek V3.1 Terminus89.77
7DeepSeek V3.189.02
8DeepSeek V3.1 (Thinking)88.82
9DeepSeek R1 052887.61
10Qwen 3 Coder Plus86.79
11GPT-4o (2024-11-20)73.14

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