Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Property Comparison & Ranking on PolyBench (test)

77MCQ Accuracy

GPT-5

17.7233.1148.563.89Jan 22, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.01
7790
2026.01
6986
2026.01
6685
2026.01
6571
2026.01
6373
2026.01
6170
2026.01
5969
2026.01
5785
2026.01
5569
2026.01
5568
2026.01
5450
2026.01
5087
2026.01
4960
2026.01
4857
2026.01
4651
2026.01
4358
2026.01
4247
2026.01
3956
2026.01
2049