Shader Benchmark: leaderboard
Shader Benchmark (nbardy) — generating shader programs from natural-language prompts, graded by an LLM judge panel with render failures counting as zero; average judge score (0-500).
Metric: Avg judge score (0-500, render fails count 0). Source: nbardy.github.io. Saturation forecast: Around May 2028. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 (High) | 242.2 | #31 (GPT-5.5) |
| 2 | Claude Opus 4.7 | 235.2 | #49 |
| 3 | Gemini 3.1 Pro (Preview) | 224 | #58 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=shader-benchmark · How It Works · Data refreshed daily, snapshot 2026-10-20.