Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

PHYX

Benchmarks

Task NameDataset NameSOTA ResultTrend
Physical ReasoningPhyX
Accuracy48.6
16
Multimodal AutoformalizationPHYX Thermodynamics
Compile Rate20
10
Multimodal AutoformalizationPHYX Electromagnetism
Compile Success Rate0.667
10
Multimodal AutoformalizationPHYX Mechanics
Compile Rate71.4
10
Multimodal AutoformalizationPHYX Modern
Compile Rate71.4
10
Showing 5 of 5 rows