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
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 235B A22B 2507 Instruct | 43.8 |
| 2 | Qwen 2.5 72B Instruct | 37.1 |
| 3 | DeepSeek V3 | 36 |
| 4 | Llama 3.3 70B Instruct | 33.7 |
| 5 | Llama 3.1 8B Instruct | 18 |
Interactive version: theaggregate.ai/benchmark?slug=mat-pref-iid · How It Works · Data refreshed daily, snapshot 2026-09-26.