Mat-Pref - IID: leaderboard

Metric: Logical-question accuracy (%; majority vote over each logical question's distractor permutations, three- or four-choice ionic substitution questions graded against Materials Project DFT values; 89 logical questions on held-out hosts of the eight training structure families). Source: arxiv.org. Saturation forecast: Around December 2026. 9 models tracked.

Top models

#ModelScore
1Qwen 3 235B A22B 2507 Instruct43.8
2Qwen 2.5 72B Instruct37.1
3DeepSeek V336
4Llama 3.3 70B Instruct33.7
5Llama 3.1 8B Instruct18

Interactive version: theaggregate.ai/benchmark?slug=mat-pref-iid · How It Works · Data refreshed daily, snapshot 2026-09-26.