BIG-Bench Hard

BIG-Bench Hard (BBH) - a subset of 23 challenging BIG-Bench tasks. few-shot.

Category

Reasoning

Max Score

100.0

Score Type

percent

Active

Yes

Model Scores

Scores for BIG-Bench Hard

Model Score Date Verified
Gemma 3 1B PT
28.40
27.02.2025 Verified
Gemma 3 4B PT
38.66%
27.02.2025 Verified
Gemma 3 12B PT
75.94%
27.02.2025 Verified
Gemma 3 27B PT
84.71%
27.02.2025 Verified
GLM-5.3-Flash
100.00%
27.08.2026 Verified