StudentBench - Lesson Planning: leaderboard
Metric: Expert tutor pairwise preference, Bradley-Terry score (lesson plans). Source: studentbench.org. Saturation forecast: Around December 2027. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 5 (High) | 1.1 |
| 2 | Claude Opus 4.8 (xHigh) | 0.91 |
| 3 | GPT-5.5 (High) | 0.88 |
| 4 | Claude Opus 4.8 (Non-reasoning) | 0.59 |
| 5 | Claude Sonnet 4.6 (Low) | 0.4 |
| 6 | Claude Sonnet 5 (Low) | 0.03 |
| 7 | Gemini 3.7 Flash (Medium) | -0.42 |
| 8 | Gemini 3.1 Pro (Preview) (High) | -0.92 |
| 9 | GPT-5.4 Mini (Non-reasoning) | -1.04 |
| 10 | Gemma 4 31B (High) | -1.14 |
| 11 | Gemini 3.5 Flash (Low) | -1.32 |
Interactive version: theaggregate.ai/benchmark?slug=studentbench-lesson-planning · How It Works · Data refreshed daily, snapshot 2026-10-04.