ModelsLeaderboardHardwareEvalsTrainRentalsAPI Docs
Language

Big-Bench Hard

Official

A collection of challenging BIG-Bench tasks selected because prior models performed poorly. Covers symbolic reasoning, algorithmic reasoning, and language understanding.

Source
Category: reasoningEval type: LM-Eval runVersion: v1.0Submitted by: Community
LM-Eval run: run lm-eval-harness locally, then submit the task scores and optional artifacts to POST /api/evals/runs.

Eval Details

Scoring
Exact Match
Aggregation
Mean
Direction
Higher is better
Tasks
1 task

Default Run Config

Seed: 42FewShot: 3
TaskDatasetWeightShotsMax Tokens
Big-Bench Hard
bbh
Not specified13-shot—

Leaderboard— best run per model

No approved results yet. Submit a run via the API.