MatPhaseBench: leaderboard
Metric: BERTScore recall (baseline-rescaled XLNet-large BERTScore, at most 1 and unbounded below in principle, mean over the 200 diagrams; free-form description of each of the 200 literature phase diagrams, prompted zero-shot with its annotated semantic dimensions, compared with the expert description from the source paper; temperature 0). Source: arxiv.org. Saturation forecast: Around 2030. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.8 | 0.41 |
| 2 | GLM-5V Turbo | 0.4 |
| 3 | GPT-5.5 | 0.39 |
| 4 | Gemini 3.1 Pro (Preview) | 0.39 |
| 5 | Qwen 3.6 Plus | 0.39 |
| 6 | Qwen 3.6 27B | 0.38 |
| 7 | Qwen 3.6 35B A3B | 0.38 |
| 8 | Qwen 3.6 Flash | 0.38 |
| 9 | GLM-4.6V | 0.37 |
| 10 | Gemini 3.1 Flash Lite | 0.36 |
| 11 | Llama 4 Maverick | 0.3 |
| 12 | Llama 4 Scout | 0.3 |
Interactive version: theaggregate.ai/benchmark?slug=matphasebench · How It Works · Data refreshed daily, snapshot 2026-09-29.