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

Tool-using Reasoning on Reasoning Domain Suite (AIME2024, AIME2025, HotpotQA, 2WikiMultihopQA, Musique)

42.39Average Accuracy

TEPOdense

18.324424.572230.8237.0678Feb 2, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
42.393.99
2026.02
39.013.6
2026.02
38.931.97
2026.02
37.921.67
2026.02
37.92.96
2026.02
37.771.64
2026.02
37.371.79
2026.02
37.23.98
2026.02
36.431.66
2026.02
36.392.02
2026.02
31.745.42
2026.02
25.481.98
2026.02
19.253.45