evals.report
BenchmarksLabsCompareRun guides
BenchmarksReasoning

BIG-Bench Extra Hard

A general-reasoning benchmark from Google DeepMind that replaces each of the 23 BIG-Bench Hard (BBH) tasks with a novel, substantially harder task probing the same skill, measuring broad reasoning (many-hop, causal, spatial, temporal, geometric, linguistic, logic-puzzle, and humor) rather than just math and coding.

Reasoningharmonic mean accuracyHigher is better

What this benchmark measures

A general-reasoning benchmark from Google DeepMind that replaces each of the 23 BIG-Bench Hard (BBH) tasks with a novel, substantially harder task probing the same skill, measuring broad reasoning (many-hop, causal, spatial, temporal, geometric, linguistic, logic-puzzle, and humor) rather than just math and coding.

Rows on this page are sourced from public benchmark artifacts, leaderboard exports, or source-linked model reports. Each row keeps benchmark version, source model name, and available run details attached to the score.

The metric shown here is harmonic mean accuracy. It should be interpreted within BIG-Bench Extra Hard, not compared as part of a site-wide ranking.

No composite ranking
evals.report never combines benchmarks. harmonic mean accuracy on BIG-Bench Extra Hard is its own number — don’t average it with other metrics.