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

Scientific Reasoning on GPQA (avg@16)

44.1avg@16

Qwen2.5-32B-Instruct

25.06830.00934.9539.891Mar 19, 2026
Updated 29d ago

Evaluation Results

MethodLinks
2026.03
44.1
2026.03
37
2026.03
36.3
2026.03
36
2026.03
35
2026.03
34.7
2026.03
34.4
2026.03
34.1
2026.03
32.8
2026.03
30.5
2026.03
30.5
2026.03
30.2
2026.03
29.7
2026.03
29.5
2026.03
29.5
2026.03
28.8
2026.03
28.7
2026.03
28.3
2026.03
28
2026.03
27.7
2026.03
26.8
2026.03
26.6
2026.03
26.4
2026.03
26.4
2026.03
26.1
2026.03
26.1
2026.03
26
2026.03
25.8