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

General Reasoning on BBH

88.7Score

DeepSeek V3.2

66.13271.99177.8583.709Feb 11, 2026Feb 14, 2026Feb 18, 2026Feb 21, 2026Feb 25, 2026Feb 28, 2026Mar 4, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
88.7---
2026.02
88.7---
2026.02
88.5---
2026.02
88.2---
2026.02
88.2---
2026.02
86.2---
2026.03
69---
2026.03
68---
2026.03
68---
2026.03
68---
2026.03
67---
2026.03
67---
2026.02
---47.38
2026.02
---46.66
2026.02
---53.66
2026.02
---53.66
2026.02
---46.6
2026.02
---46.67
2026.02
---55.59
2026.02
---54.47
2025.02
-1720-
2025.02
-1010-
2025.02
-2250-
2025.02
-4140-
2025.02
-3270-
2025.02
-4580-
2025.02
-48100-
2025.02
-4790-