language benchmark
BBH Leaderboard
BBH is a suite of 23 challenging tasks selected from BIG-Bench to evaluate multi-step reasoning across diverse domains.
Updated Sep 5, 2026
Models12
Model coverage12
MetricScore
EvidenceB
BBH Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score88.87% | Percentile100.00% | Participants12 | EvidenceC | Evaluated |
| Rank02 | ModelXI | Score88.40% | Percentile90.91% | Participants12 | EvidenceC | Evaluated |
| Rank03 | ModelAM Nova ProAmazon | Score86.90% | Percentile81.82% | Participants12 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score84.50% | Percentile72.73% | Participants12 | EvidenceC | Evaluated |
| Rank05 | ModelDE | Score84.30% | Percentile63.64% | Participants12 | EvidenceC | Evaluated |
| Rank06 | ModelAMNova LiteAmazon | Score82.40% | Percentile54.55% | Participants12 | EvidenceC | Evaluated |
| Rank07 | ModelAC | Score82.40% | Percentile45.45% | Participants12 | EvidenceC | Evaluated |
| Rank08 | ModelOP | Score81.55% | Percentile36.36% | Participants12 | EvidenceC | Evaluated |
| Rank09 | ModelAMNova MicroAmazon | Score79.50% | Percentile27.27% | Participants12 | EvidenceC | Evaluated |
| Rank10 | ModelAC | Score78.20% | Percentile18.18% | Participants12 | EvidenceC | Evaluated |
| Rank11 | ModelNR | Score67.82% | Percentile9.09% | Participants12 | EvidenceC | Evaluated |
| Rank12 | ModelBA | Score30.40% | Percentile0.00% | Participants12 | EvidenceC | Evaluated |
BBH Highlights
The leading models and scores on this benchmark.
BBH Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for BBH
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is BBH?
What BBH measures and how its scores work.
Big-Bench Hard (BBH) is a suite of 23 tasks selected from BIG-Bench for which prior language model evaluations did not outperform the average human-rater.
BBH measures multi-step reasoning across arithmetic, logical reasoning, reading comprehension, and commonsense reasoning, including temporal understanding, spatial reasoning, causal understanding, and deductive logical reasoning; its metric is Score, reported as a ratio.
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
- No
- Evaluation key
- overall
LLM Stats. 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 88.87%.
What are the top three models on BBH?
The current leaders are Qwen3 235B A22B (88.87%), MiMo-V2.5-Pro (88.40%), and Nova Pro (86.90%).
Which BBH model has the lowest official input price?
Nova Micro has the lowest matched official input price at $0.04 input / $0.14 output per 1M tokens.
Which models are fastest among BBH results?
The fastest matched records are DeepSeek-V2.5 (100.00 tok/s via DeepSeek), Qwen3 235B A22B (21.74 tok/s via DeepInfra), and MiMo-V2.5-Pro (5.27 tok/s via DeepInfra).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.