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

Multi-hop Reasoning on MuSR

43.12Accuracy

Qwen3 8B

37.483238.946640.4141.8734Feb 11, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
43.12
2026.02
42.06
2026.02
41.4
2026.02
41
2026.02
39.94
2026.02
39.81
2026.02
39.68
2026.02
38.36
2026.02
38.1
2026.02
37.7