chemeval

1 个项目 · ⭐ 34

USTC-StarTeam/ChemEval

ICLR 2026 | ChemEval: 4-level, 13-dimension, 62-task text/multimodal chemistry benchmark for evaluating LLMs and MLLMs.

Python ⭐ 34 ⑂ 1 NOASSERTION · 2026-06-09推送

benchmark large-language-models

2026-06-09