Spaces:
Running
Running
Commit History
13 days ago
-
Replace old benchmark with agent and world-model evaluation galleries
Verified signature9d71edb
-
Add configurable model selector and model-specific result downloads
Verified signature159070f -
Preserve success probability in accuracy and calibration views
Verified signaturec2669bd -
Show classification accuracy by probability and confidence
Verified signature998ce41 -
Add success probability calibration plot with bin counts
Verified signature97598a5 -
Use neutral early-sample timing labels
Verified signaturea8acadd -
Simplify summary to accuracy by difficulty and recorded outcome
Verified signaturefd1df4f -
Show accuracy by difficulty and sample type with filters
Verified signaturecc089f4 -
Upload folder using huggingface_hub
Verified signature2f26975 -
initial commit
Verified signature09ce7ec