Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Error Identification on PeanoBench 21 incorrect proofs

3.4Accuracy

Baseline

3.233.3153.43.485Jun 10, 2025Jul 18, 2025Aug 25, 2025Oct 2, 2025Nov 9, 2025Dec 17, 2025Jan 24, 2026
Updated 4mo ago

Evaluation Results

MethodLinks
2026.01
3.43.54.54.6
2026.01
3.43.84.34.5
2025.06
3.43.54.54.6
2025.06
3.43.84.34.5