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

Knowledge Reasoning on GPQA Diamond

64.1Accuracy (avg@8)

Qwen3

35.60443.00250.457.798Dec 18, 2025Jan 6, 2026Jan 25, 2026Feb 14, 2026Mar 5, 2026Mar 24, 2026Apr 13, 2026
Updated 5d ago

Evaluation Results

MethodLinks
2026.04
64.1
2026.04
62.1
2026.04
58.9
2026.04
55.6
2025.12
47.1
2025.12
46.4
2026.04
46
2025.12
43.2
2026.04
40.2
2025.12
40.1
2025.12
36.8
2026.04
36.7