SciEval (K-12) - Quadratic Weighted Kappa: leaderboard

Metric: Quadratic weighted kappa (x100, -100 to 100) between the predicted and expert criterion scores on the held-out test set of SciEval, a K-12 science instructional-material evaluation benchmark: given an NGSS lesson as page-marked PDF text and one EQuIP rubric criterion, the model returns a 0-3 score and the supporting evidence as JSON, simplified prompt, temperature 0; failed predictions are left out; higher is better. Source: arxiv.org. Saturation forecast: Around 2031. 6 models tracked.

Top models

#ModelScore
1Qwen 3 4B 2507 Instruct16.23
2Gemini 2.0 Flash5.7
3Llama 3.1 8B Instruct4.58
4Llama 3.2 3B Instruct4.52
5GPT-4o Mini4.02

Interactive version: theaggregate.ai/benchmark?slug=scieval-k-12-quadratic-weighted-kappa · How It Works · Data refreshed daily, snapshot 2026-10-07.