Atlas

AI labs

AI labsUnited States

LM-Provers models

LM-Provers is an open research team developing language models, datasets, graders, and benchmarks for mathematical theorem proving. Its releases include the QED-Nano proof model and artifacts such as FineProofs, IMOProofBench, ProofBench, and theorem-proof grading benchmarks.

huggingface.co

Scored models
1
Best ranked
QED-Nano #297 of 896
Newest
QED-Nano Feb 12, 2026
Open weights
1 of 1

LM-Provers models ranked by capability

Capability is Atlas's single score for each model, fitted to every sourced benchmark result (methodology). Rank is among all 896 ranked models from every lab.

ModelReleasedCapabilityRankBenchmarksWeights
QED-NanoFeb 12, 2026136.1#29714Open

All AI labsOpen-weight LLM leaderboard