OpenCodePapers

physics-question-answering-on-critpt

Question AnsweringPhysics Question Answering
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeAccuracyModelNameReleaseDate
Kimi K3: Open Frontier Intelligence✓ Link23.4Kimi K3 Max2026-07-27
Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition✓ Link20.0Sage-A1.52026-10-20
Hy4 preview✓ Link16.9Hy4 preview2026-08-28
Introducing Beam: Reflection's 501B open-weight model16.3Beam2026-10-05
Magenta: Closing the Loop Between Mathematical Reasoning and Lean Verification8.6K2-Horizon-375B-A23B2026-09-10
Inkling-Small✓ Link8.3Inkling-Small2026-07-27
Motif 3: Technical Report✓ Link6.6Motif 32026-08-10