StudentBench - Lesson Planning: leaderboard

Expert human tutors compare pairs of GRE lesson plans written by AI tutors on five criteria; preferences are fitted to a Bradley-Terry score centred on zero. Each row is one model at one reasoning setting. Higher is better. Source: studentbench.org.

Metric: Expert tutor pairwise preference, Bradley-Terry score (lesson plans). Source: studentbench.org. Saturation forecast: Around November 2027. 12 models tracked. Updated 4 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1Claude Opus 5High1.1#26
2GPT-5.5 ProMedium0.95#40
3Claude Opus 4.8xHigh0.91#64
4GPT-5.5High0.88#54
5Claude Sonnet 4.6Low0.4#175
6Claude Sonnet 5Low0.03#118
7Kimi K2.6Medium-0.03#192
8Gemini 3.7 FlashMedium-0.42#42
9Gemini 3.1 Pro (Preview)High-0.92#101
10GPT-5.4 MiniNon-reasoning-1.04#405
11Gemma 4 31BHigh-1.14#389
12Gemini 3.5 FlashLow-1.32#108

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=studentbench-lesson-planning · How It Works · Data refreshed daily, snapshot 2026-11-20.