Shader Benchmark — leaderboard
Metric: Avg judge score (0-500, render fails count 0). Source: nbardy.github.io. 3 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 (High) | 242.2 |
| 2 | Claude Opus 4.7 | 235.2 |
| 3 | Gemini 3.1 Pro (Preview) | 224 |
Interactive version: aibenchmarks.dev/benchmark?slug=shader-benchmark · How the rankings work · Data refreshed daily, snapshot 2026-07-06.