# BBH leaderboard

Reasoning benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/leaderboards/benchmarks/reasoning-bbh

BIG-Bench Hard. Every model the catalog carries a published BBH value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Reasoning |
| Measure | Mixed reasoning tasks |
| Tasks | 23 tasks |
| Difficulty | Advanced reasoning |
| Published by | [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://arxiv.org/abs/2210.09261) |

A suite of 23 challenging tasks from the BIG-Bench collaborative benchmark where prior language models failed to exceed average human performance, even with chain-of-thought prompting.

## BBH ranking

9 models with a published BBH value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Mixed reasoning tasks | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Claude 3.5 Haiku](https://modelchoice.dev/models/claude-3-5-haiku) | Anthropic | 86.6 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Soofi S 30B-A3B](https://modelchoice.dev/models/soofi-s-30b-a3b) | Soofi Project | 78.8 | Observed 2026-11-21 · source benchlm:models |
| 3 | [MiniCPM5-1B](https://modelchoice.dev/models/minicpm5-1b) | OpenBMB | 71.89 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Phi-3.5-mini](https://modelchoice.dev/models/phi-3-5-mini) | Microsoft | 69 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Granite-4.0-1B](https://modelchoice.dev/models/granite-4-0-1b) | IBM | 60.37 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Granite-4.0-H-1B](https://modelchoice.dev/models/granite-4-0-h-1b) | IBM | 59.68 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Gemma 4 12B](https://modelchoice.dev/models/gemma-4-12b) | Google | 53 | Last good 2026-10-08 · source benchlm:models |
| 8 | [Granite-4.0-H-350M](https://modelchoice.dev/models/granite-4-0-h-350m) | IBM | 33.28 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Granite-4.0-350M](https://modelchoice.dev/models/granite-4-0-350m) | IBM | 33.07 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
