OpenLearnLM - Pedagogical Knowledge: leaderboard

Metric: Accuracy (%; four-option multiple choice from teacher certification exams). Source: arxiv.org. Saturation forecast: Estimated already saturated. 7 models tracked.

Top models

#ModelScore
1Gemini 3 Pro89.6
2GLM-4.787.5
3Kimi K2 (Thinking)87.1
4Claude Opus 4.586.1
5Grok 4.1 Fast86.1
6GPT-5.284.6
7DeepSeek V3.273.2

Interactive version: theaggregate.ai/benchmark?slug=openlearnlm-pedagogical-knowledge · How It Works · Data refreshed daily, snapshot 2026-09-25.