Reconstruction (Research Idea Recovery) - Medicine: leaderboard

Metric: Match rate (%; the 78 medicine seed papers; share of a model's five hypotheses, proposed in one call from a published paper's pre-publication bibliography only (titles and abstracts under anonymous IDs, the paper itself and later literature withheld), that an LLM judge matches to the held-out paper's idea; mean over the six other evaluated models as leave-one-out judges). Source: arxiv.org. Saturation forecast: Around 2029. 7 models tracked.

Top models

#ModelScore
1GPT-5.6 Pro Sol14.6
2Claude Opus 4.814.2
3Kimi K311.1
4Gemini 3.1 Pro (Preview)10.5
5GLM-5.210.1
6DeepSeek V4 Pro6.9
7Qwen 3.7 Max4.8

Interactive version: theaggregate.ai/benchmark?slug=reconstruction-research-idea-recovery-medicine · How It Works · Data refreshed daily, snapshot 2026-09-26.