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

Knowledge Reasoning on GPQA

67.3Accuracy

LLaDA-2.1-flash

35.122443.476251.8360.1838Dec 29, 2025Jan 15, 2026Feb 2, 2026Feb 19, 2026Mar 9, 2026Mar 26, 2026Apr 13, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
67.3
2026.04
65
2026.04
62.3
2026.04
58.7
2025.12
55.55
2026.04
55.4
2026.04
54.9
2026.04
53.3
2025.12
52.02
2025.12
50.5
2025.12
50.5
2025.12
49.49
2025.12
47.48
2025.12
46.96
2025.12
45.96
2025.12
42.42
41.41
2025.12
36.36