WebCoderBench - Performance — leaderboard
Metric: Score (%). Source: huggingface.co. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 Coder Plus | 98.54 |
| 2 | DeepSeek V3.1 Terminus | 98.19 |
| 3 | GPT-5 (High) | 98.08 |
| 4 | DeepSeek V3.1 (Thinking) | 97.97 |
| 5 | DeepSeek V3.1 | 97.6 |
| 6 | GLM-4.5 | 97.21 |
| 7 | MiniMax-M2 | 97.15 |
| 8 | DeepSeek R1 0528 | 97.02 |
| 9 | GPT-5 Codex (High) | 94.44 |
| 10 | Gemini 2.5 Pro | 94.32 |
| 11 | GPT-4o (2024-11-20) | 94.07 |
Interactive version: aibenchmarks.dev/benchmark?slug=webcoderbench-performance · How the rankings work · Data refreshed daily, snapshot 2026-07-12.