Beta
BenchmarksReading · ~3 min · 50 words deep

BBH

BBH is a reasoning benchmark tracked by BenchGecko across every frontier and open-weight model.

BBH leaderboard
TL;DR

BBH is a reasoning benchmark tracked by BenchGecko across every frontier and open-weight model.

Level 1

BBH is a reasoning benchmark tracked by BenchGecko across every frontier and open-weight model.

Level 2

BBH is a reasoning benchmark tracked by BenchGecko across every frontier and open-weight model. BenchGecko tracks BBH scores for every eligible frontier and open-weight model. The metric is % with a maximum of 100. Category · reasoning. Source · public leaderboard. See the live leaderboard for the current top 10.

Level 3

BBH is a reasoning benchmark tracked by BenchGecko across every frontier and open-weight model. Technical details: the benchmark uses % scored against 100 as max. Primary category is reasoning. Source ingestion runs through the public leaderboard with the update cadence documented on the methodology page. Correlations with downstream capability have been studied in the public literature and the benchmark's authors' release notes.

The takeaway for you
If you are a
Researcher
  • ·BBH measures reasoning capability with % scoring
  • ·Source: public leaderboard · tracked on BenchGecko's /benchmark page
  • ·Used to compare frontier models on reasoning-specific tasks
If you are a
Builder
  • ·Pick models with high BBH if your workload matches reasoning
  • ·Benchmark scores correlate with real-world quality only for matched task types
  • ·Check the live leaderboard before locking in a model · rankings shift weekly
If you are a
Investor
  • ·BBH is one of the citations labs use in launch announcements
  • ·Saturation at the top of the leaderboard signals the benchmark is aging
  • ·Watch for new benchmarks when all frontier models cluster within 2 points
If you are a
Curious · Normie
  • ·BBH is a test that scores how good an AI is at reasoning
  • ·Higher score = better model on that specific kind of task
  • ·Not every score matters for every use · match the test to your goal
Gecko's take

BBH rewards models that spend test-time compute · reasoning tier premium priced in.

BBH is a reasoning benchmark tracked by BenchGecko across every frontier and open-weight model.