# Claude 3.5 Haiku Benchmark Scores & Performance

> Claude 3.5 Haiku by Anthropic has 10 source-displayable benchmark rows but no public overall score. It remains unranked.

Canonical page: https://benchlm.ai/models/claude-3-5-haiku

Last updated: October 14, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | Anthropic |
| Source Type | Proprietary |
| Reasoning Type | Non-Reasoning |
| Context Window | 200K |
| Official model card | [Claude 3.5 Haiku model card addendum](https://assets.anthropic.com/m/1cd9d098ac3e6467/original/Claude-3-Model-Card-October-Addendum.pdf) |
| Overall Score | Not computed (unranked) |
| Overall Rank | Unranked |

## Family & Coverage

- Family: Claude 3.5 Haiku
- Variant: base
- Benchmarks covered: 10 of 628
- Coverage note: Published evidence is shown below; no public overall score is assigned.

## Coding Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [HumanEval](/benchmarks/humaneval) | 88.1% | [Anthropic: Claude 3.5 Haiku and upgraded Claude 3.5 Sonnet model card addendum](https://assets.anthropic.com/m/1cd9d098ac3e6467/original/Claude-3-Model-Card-October-Addendum.pdf) |
| [SWE-bench Verified](/benchmarks/swe-bench-verified) | 40.6% | [Anthropic: Claude 3.5 Haiku and upgraded Claude 3.5 Sonnet model card addendum](https://assets.anthropic.com/m/1cd9d098ac3e6467/original/Claude-3-Model-Card-October-Addendum.pdf) |

## Reasoning Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [BBH](/benchmarks/bbh) | 86.6% | [Anthropic: Claude 3.5 Haiku and upgraded Claude 3.5 Sonnet model card addendum](https://assets.anthropic.com/m/1cd9d098ac3e6467/original/Claude-3-Model-Card-October-Addendum.pdf) |
| [DROP](/benchmarks/drop) | 83.1% | [Anthropic: Claude 3.5 Haiku and upgraded Claude 3.5 Sonnet model card addendum](https://assets.anthropic.com/m/1cd9d098ac3e6467/original/Claude-3-Model-Card-October-Addendum.pdf) |

## Knowledge Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [GPQA](/benchmarks/gpqa) | 41.6% | [Anthropic: Claude 3.5 Haiku and upgraded Claude 3.5 Sonnet model card addendum](https://assets.anthropic.com/m/1cd9d098ac3e6467/original/Claude-3-Model-Card-October-Addendum.pdf) |
| [MMLU-Pro](/benchmarks/mmlu-pro) | 65% | [Anthropic: Claude 3.5 Haiku and upgraded Claude 3.5 Sonnet model card addendum](https://assets.anthropic.com/m/1cd9d098ac3e6467/original/Claude-3-Model-Card-October-Addendum.pdf) |
| [MMLU](/benchmarks/mmlu) | 80.3% | [Anthropic: Claude 3.5 Haiku and upgraded Claude 3.5 Sonnet model card addendum](https://assets.anthropic.com/m/1cd9d098ac3e6467/original/Claude-3-Model-Card-October-Addendum.pdf) |

## Instruction Following Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [IFEval](/benchmarks/ifeval) | 85.9% | [Anthropic: Claude 3.5 Haiku and upgraded Claude 3.5 Sonnet model card addendum](https://assets.anthropic.com/m/1cd9d098ac3e6467/original/Claude-3-Model-Card-October-Addendum.pdf) |

## Multilingual Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [MGSM](/benchmarks/mgsm) | 85.6% | [Anthropic: Claude 3.5 Haiku and upgraded Claude 3.5 Sonnet model card addendum](https://assets.anthropic.com/m/1cd9d098ac3e6467/original/Claude-3-Model-Card-October-Addendum.pdf) |

## Mathematics Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [AIME 2024](/benchmarks/aime2024) | 5.3% | [Anthropic: Claude 3.5 Haiku and upgraded Claude 3.5 Sonnet model card addendum](https://assets.anthropic.com/m/1cd9d098ac3e6467/original/Claude-3-Model-Card-October-Addendum.pdf) |

## Other Anthropic Models

- [Claude Opus 5.5](/models/claude-opus-5-5) - Score: 86.05
- [Claude Fable 5.1](/models/claude-fable-5-1) - Score: 82.64
- [Claude Sonnet 5.5](/models/claude-sonnet-5-5) - Score: 82.41
- [Claude Fable 5](/models/claude-fable) - Score: 80.9
- [Claude Opus 5](/models/claude-opus-5) - Score: 79.3
- [Claude Haiku 5.5](/models/claude-haiku-5-5) - Score: 71.34
- [Claude Opus 4.8](/models/claude-opus-4-8) - Score: 69.08
- [Claude Opus 4.7 (Adaptive)](/models/claude-opus-4-7-adaptive) - Score: 67.96
- [Claude Opus 4.7](/models/claude-opus-4-7) - Score: 65.18
- [Claude Sonnet 5](/models/claude-sonnet-5) - Score: 64.26
- [Claude Opus 4.6](/models/claude-opus-4-6) - Score: 61.13
- [Claude Sonnet 4.6](/models/claude-sonnet-4-6) - Score: 55.63
- [Claude Opus 4.5 Thinking](/models/claude-opus-4-5-thinking) - Score: 53.82
- [Claude Opus 4.5](/models/claude-opus-4-5) - Score: 53.77
- [Claude Sonnet 4.5](/models/claude-sonnet-4-5) - Score: 48.29
- [Claude Haiku 4.5](/models/claude-haiku-4-5) - Score: 40.93
- [Claude 4.1 Opus](/models/claude-4-1-opus) - Score: 39.89
- [Claude 4.1 Opus Thinking](/models/claude-4-1-opus-thinking) - Score: 39.2
- [Claude 4 Sonnet](/models/claude-4-sonnet) - Score: 37.94
- [Claude 3 Opus](/models/claude-3-opus) - Score: 28.38
- [Claude 3.5 Sonnet](/models/claude-3-5-sonnet) - Score: 27.62
- [Claude 3 Haiku](/models/claude-3-haiku) - Score: 14
- [Claude Mythos 5](/models/claude-mythos-5) - Score: not computed
- [Claude 4 Opus Thinking](/models/claude-4-opus-thinking) - Score: not computed
- [Claude 3.7 Sonnet Thinking](/models/claude-3-7-sonnet-thinking) - Score: not computed
- [Claude Opus 4.6 (Adaptive)](/models/claude-opus-4-6-thinking) - Score: not computed
- [Claude 4 Opus](/models/claude-4-opus) - Score: not computed
- [Claude 3.7 Sonnet](/models/claude-3-7-sonnet) - Score: not computed
- [Claude Sonnet 4.5 Thinking](/models/claude-sonnet-4-5-thinking) - Score: not computed
- [Claude Mythos 5.1](/models/claude-mythos-5-1) - Score: not computed
- [Claude Mythos Preview](/models/claude-mythos-preview) - Score: not computed
- [Claude Haiku 4.5 Thinking](/models/claude-haiku-4-5-thinking) - Score: not computed