LitXBench - Materials: leaderboard

LitXBench (2026) tests extracting complete experiments from scientific papers: on LitXAlloy, 19 alloy papers with 1,426 annotated measurements, the model writes each material with its processing chain, microstructure and measurements as Python objects from the OCR text of the paper. F1 from 0 to 1 on the set of extracted materials, for language models called through an API; higher is better.

Metric: Material F1 (0-1), whether the right set of materials is extracted for extracting every experiment (materials, process chains, microstructure configurations and measurements) as Python objects from the OCR text of LitXAlloy's 19 alloy papers (1,426 measurements; figures excluded), extracted materials matched to the annotated ones by the Hungarian algorithm, mean of three runs; models called through the API with Pydantic AI; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 6 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1Gemini 3 Flash (Preview)0.97#152
2GPT-5.2High0.97#185
3Gemini 3.1 Pro (Preview)0.96#99
4Claude Haiku 4.50.94#583
5GPT-5 Mini0.94#364
6Claude Opus 4.60.91#113

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=litxbench-materials · How It Works · Data refreshed daily, snapshot 2026-11-21.