WebCoderBench - Visual Experience — leaderboard
Metric: Score (%). Source: huggingface.co. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 Codex (High) | 93.83 |
| 2 | GPT-5 (High) | 90.62 |
| 3 | GLM-4.5 | 87.42 |
| 4 | DeepSeek V3.1 Terminus | 86.4 |
| 5 | Gemini 2.5 Pro | 78.08 |
| 6 | GPT-4o (2024-11-20) | 59.13 |
| 7 | MiniMax-M2 | 56.47 |
| 8 | DeepSeek R1 0528 | 54.36 |
| 9 | Qwen 3 Coder Plus | 46.27 |
| 10 | DeepSeek V3.1 (Thinking) | 41.12 |
| 11 | DeepSeek V3.1 | 40.65 |
Interactive version: aibenchmarks.dev/benchmark?slug=webcoderbench-visual-experience · How the rankings work · Data refreshed daily, snapshot 2026-07-12.