LH-Bench (Programmatic Content): leaderboard
Metric: Artifact score on the five-point rubric (0-1, times 100): a Gemini 3.1 Pro judge scores each rendered course chapter against SME-authored rubrics (content relevance, visual design, pedagogy, audio-visual synchronization, technical accuracy), normalized and averaged per course over 41 courses (183 chapters), the model generating the content as an autonomous agent in its vendor's harness; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 | 61.2 | #60 |
| 2 | Gemini 3.1 Pro (Preview) | 52.6 | #54 |
| 3 | GPT-5.2 | 47.8 | #105 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=lh-bench-programmatic-content · How It Works · Data refreshed daily, snapshot 2026-10-11.