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

Scientific Knowledge Evaluation on GPQA

36.16Accuracy

Qwen3 8B

22.546426.080729.61533.1493Feb 11, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
36.16
2026.02
31.45
2026.02
29.19
2026.02
28.85
2026.02
28.61
2026.02
28.36
2026.02
26.01
2026.02
25.59
2026.02
24.75
2026.02
23.07