language benchmark
BBH
Big-Bench Hard (BBH) is a suite of 23 challenging tasks selected from BIG-Bench for which prior language model evaluations did not outperform the average human-rater. These tasks require multi-step reasoning across diverse domains including arithmetic, logical reasoning, reading comprehension, and commonsense reasoning. The benchmark was designed to test capabilities believed to be beyond current language models and focuses on evaluating complex reasoning skills including temporal understanding, spatial reasoning, causal understanding, and deductive logical reasoning.
Updated Aug 11, 2026
Models12
Model coverage12
MetricScore
EvidenceB
BBH Ranking
Higher score ranks better on this benchmark.
| 01 | AC | 88.9% | 100.0% | 12 | C | |
| 02 | XI | 88.4% | 90.9% | 12 | C | |
| 03 | AM Nova ProAmazon | 86.9% | 81.8% | 12 | C | |
| 04 | AC | 84.5% | 72.7% | 12 | C | |
| 05 | DE | 84.3% | 63.6% | 12 | C | |
| 06 | AMNova LiteAmazon | 82.4% | 54.5% | 12 | C | |
| 07 | AC | 82.4% | 45.5% | 12 | C | |
| 08 | OP | 81.5% | 36.4% | 12 | C | |
| 09 | AMNova MicroAmazon | 79.5% | 27.3% | 12 | C | |
| 10 | AC | 78.2% | 18.2% | 12 | C | |
| 11 | NR | 67.8% | 9.1% | 12 | C | |
| 12 | BA | 30.4% | 0.0% | 12 | C |
BBH Score Distribution
A closer view of the leading scores on this benchmark.
BBH Highlights
The leading models and scores on this benchmark.
What is BBH?
What BBH measures and how its scores work.
Big-Bench Hard (BBH) is a suite of 23 challenging tasks selected from BIG-Bench for which prior language model evaluations did not outperform the average human-rater. These tasks require multi-step reasoning across diverse domains including arithmetic, logical reasoning, reading comprehension, and commonsense reasoning. The benchmark was designed to test capabilities believed to be beyond current language models and focuses on evaluating complex reasoning skills including temporal understanding, spatial reasoning, causal understanding, and deductive logical reasoning.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- BBH
- Modality
- text
- Primary category
- language
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- bbh|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about BBH.
Which model scores highest on BBH?
Qwen3 235B A22B is currently ranked first with 88.9%.
What does BBH measure?
Big-Bench Hard (BBH) is a suite of 23 challenging tasks selected from BIG-Bench for which prior language model evaluations did not outperform the average human-rater. These tasks require multi-step reasoning across diverse domains including arithmetic, logical reasoning, reading comprehension, and commonsense reasoning. The benchmark was designed to test capabilities believed to be beyond current language models and focuses on evaluating complex reasoning skills including temporal understanding, spatial reasoning, causal understanding, and deductive logical reasoning.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
12 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.