Anthropic, proprietary

# Claude 3 Haiku

> Claude 3 Haiku by Anthropic, released March 2024. Ranked #340 of 354 with a Noometry Index of 25.9. Scores, sources and comparisons.
- Canonical page: https://noometry.com/models/claude-3-haiku
- Last updated: 2026-10-10
- Title: Claude 3 Haiku Benchmarks, Price & Rank (October 2026)

Claude 3 Haiku by Anthropic ranks 340th of 354 ranked models on the Noometry Index as of October 2026, with a score of 25.9. Its strongest category is multimodal, where it ranks 128th.

Last verified October 10, 2026

## Specifications

- **Noometry rank:** #340 of 354
- **Index score:** 25.9
- **Evidence:** Confirmed 37 results
- **Provider:** [Anthropic](https://noometry.com/providers/anthropic)
- **Released:** March 7, 2024
- **Weights:** Proprietary
- **Reasoning:** Unknown
- **Context window:** —
- **Max output:** —
- **Input price:** Not listed
- **Output price:** Not listed
- **Blended price:** Not listed
- **Output speed:** 41 tokens/s [Kagi](https://help.kagi.com/kagi/ai/llm-benchmark.html)
- **Value:** Not ranked
- **Knowledge cutoff:** Unknown

## Category scores

Each category score combines every public result we have in that category.

Claude 3 Haiku category scores

1.  Coding 26.4
2.  Reasoning 16.3
3.  Math 9.8
4.  Knowledge 17.3
5.  Multimodal 23.6
6.  Multilingual 36.0
7.  Instruction Following 61.3
8.  Long Context 36.1
9.  Writing & Preference 29.7
10.  020406080

Claude 3 Haiku category ranks
| Category | Score | Rank | Results |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 26.4 | #325 | 5 |
| [Reasoning](https://noometry.com/best/reasoning) | 16.3 | #307 | 4 |
| [Math](https://noometry.com/best/math) | 9.8 | #319 | 3 |
| [Knowledge](https://noometry.com/best/knowledge) | 17.3 | #285 | 3 |
| [Multimodal](https://noometry.com/best/multimodal) | 23.6 | #128 | 1 |
| [Multilingual](https://noometry.com/best/multilingual) | 36.0 | #243 | 1 |
| [Instruction Following](https://noometry.com/best/instruction-following) | 61.3 | #247 | 1 |
| [Long Context](https://noometry.com/best/long-context) | 36.1 | #237 | 1 |
| [Writing & Preference](https://noometry.com/best/writing) | 29.7 | #291 | 4 |

## Strengths and weaknesses

Categories where Claude 3 Haiku places highest and lowest among the models ranked in each, with its score against that category's median.

### Strongest categories

Claude 3 Haiku: strongest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Long Context](https://noometry.com/best/long-context) | 36.1 | −4.9 | #237 of 296, top 81% |
| [Instruction Following](https://noometry.com/best/instruction-following) | 61.3 | −10.0 | #247 of 305, top 81% |
| [Multilingual](https://noometry.com/best/multilingual) | 36.0 | −11.4 | #243 of 297, top 82% |

### Weakest categories

Claude 3 Haiku: weakest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Multimodal](https://noometry.com/best/multimodal) | 23.6 | −14.9 | #128 of 128, top 100% |
| [Math](https://noometry.com/best/math) | 9.8 | −26.7 | #319 of 327, top 98% |
| [Coding](https://noometry.com/best/coding) | 26.4 | −12.3 | #325 of 340, top 96% |

## Closest competitors

The models ranked just above and below Claude 3 Haiku. When scores are this close, price and speed are often the better way to choose.

Models ranked closest to Claude 3 Haiku
| Model | Rank | Score | Blended $/M | Speed |  |
| --- | --- | --- | --- | --- | --- |
| [Qwen3-1.7B](https://noometry.com/models/qwen3-1-7b) | #336 | 26.6 | — | — | [Compare](https://noometry.com/compare/claude-3-haiku-vs-qwen3-1-7b) |
| [Mistral Nemo](https://noometry.com/models/mistral-nemo) | #337 | 26.4 | $0.15 | — | [Compare](https://noometry.com/compare/claude-3-haiku-vs-mistral-nemo) |
| [Ministral 3B](https://noometry.com/models/ministral-3b) | #338 | 26.2 | $0.10 | — | [Compare](https://noometry.com/compare/claude-3-haiku-vs-ministral-3b) |
| [DeepSeek-R1-Distill-Qwen-1.5B](https://noometry.com/models/deepseek-r1-distill-qwen-1-5b) | #339 | 26.1 | — | — | [Compare](https://noometry.com/compare/claude-3-haiku-vs-deepseek-r1-distill-qwen-1-5b) |
| [Gemma 2 9B](https://noometry.com/models/gemma-2-9b) | #341 | 25.9 | — | — | [Compare](https://noometry.com/compare/claude-3-haiku-vs-gemma-2-9b) |
| [Dolly 2.0-12b](https://noometry.com/models/dolly-2-0-12b) | #342 | 25.5 | — | — | [Compare](https://noometry.com/compare/claude-3-haiku-vs-dolly-2-0-12b) |
| [GPT-4o mini](https://noometry.com/models/gpt-4o-mini) | #343 | 25.5 | $0.26 | 120 | [Compare](https://noometry.com/compare/claude-3-haiku-vs-gpt-4o-mini) |
| [Llama 3-8B](https://noometry.com/models/llama-3-8b) | #344 | 25.5 | — | — | [Compare](https://noometry.com/compare/claude-3-haiku-vs-llama-3-8b) |

Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise)

## Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

### Coding

Claude 3 Haiku Coding benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [WeirdML](https://noometry.com/benchmarks/weirdml) | 9.8% | #114 of 119, top 96% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [BigCodeBench Instruct](https://noometry.com/benchmarks/bigcodebench-instruct) | 39.4% | #34 of 64, top 54% |  | [BigCodeBench](https://bigcode-bench.github.io/) | 2024-03-07 |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1199 | #241 of 294, top 82% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [BigCodeBench Complete](https://noometry.com/benchmarks/bigcodebench-complete) | 50.1% | #34 of 66, top 52% |  | [BigCodeBench](https://bigcode-bench.github.io/) | 2024-03-07 |
| [CadEval](https://noometry.com/benchmarks/cadeval) | 12% | #14 of 14, top 100% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [HumanEval+](https://noometry.com/benchmarks/humaneval-plus) | 68.9% | #22 of 45, top 49% | mar 2024 | [EvalPlus](https://evalplus.github.io/leaderboard.html) |  |
| [MBPP+](https://noometry.com/benchmarks/mbpp-plus) | 68.8% | #17 of 38, top 45% | mar 2024 | [EvalPlus](https://evalplus.github.io/leaderboard.html) |  |

### Reasoning

Claude 3 Haiku Reasoning benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Kagi LLM Benchmark](https://noometry.com/benchmarks/kagi-reasoning) | 34.2% | #89 of 99, top 90% |  | [Kagi LLM Benchmark](https://help.kagi.com/kagi/ai/llm-benchmark.html) |  |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1174 | #247 of 297, top 84% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [DTBench](https://noometry.com/benchmarks/dtbench) | 50.1% | #136 of 151, top 91% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMCA](https://noometry.com/benchmarks/lmca) | 8.8% | #115 of 125, top 92% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Epoch Capabilities Index](https://noometry.com/benchmarks/epoch-capabilities-index) | 118.35 | #177 of 213, top 84% |  | [Epoch AI](https://epoch.ai/eci) | 2024-03-07 |
| [ForecastBench](https://noometry.com/benchmarks/forecastbench) | 53.2 | #70 of 72, top 98% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WinoGrande](https://noometry.com/benchmarks/winogrande) | 74.2% | #25 of 43, top 59% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Math

Claude 3 Haiku Math benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 1.8% | #163 of 173, top 95% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-02-25 |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1188 | #235 of 285, top 83% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [MATH Level 5](https://noometry.com/benchmarks/math-level-5) | 14.9% | #68 of 79, top 87% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-01-27 |

### Knowledge

Claude 3 Haiku Knowledge benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 36.3% | #156 of 186, top 84% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-01-27 |
| [Confabulations](https://noometry.com/benchmarks/confabulations) (lower is better) | 34.2% | #48 of 51, top 95% |  | [Lech Mazur benchmarks](https://github.com/lechmazur/confabulations) |  |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1148 | #236 of 273, top 87% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [MMLU](https://noometry.com/benchmarks/mmlu) | 73.8% | #36 of 81, top 45% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Multimodal

Claude 3 Haiku Multimodal benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Vision](https://noometry.com/benchmarks/arena-vision) | 950 | #122 of 122, top 100% |  | [LMArena](https://lmarena.ai/leaderboard/vision) | 2026-10-09 |
| [ScienceQA](https://noometry.com/benchmarks/scienceqa) | 72% | #3 of 6, top 50% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Multilingual

Claude 3 Haiku Multilingual benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1178 | #243 of 297, top 82% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1155 | #245 of 285, top 86% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1195 | #194 of 223, top 87% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1174 | #198 of 231, top 86% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Japanese](https://noometry.com/benchmarks/arena-japanese) | 1102 | #186 of 211, top 89% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1109 | #188 of 213, top 89% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1204 | #232 of 283, top 82% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1166 | #202 of 226, top 90% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Instruction Following

Claude 3 Haiku Instruction Following benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1173 | #247 of 298, top 83% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Long Context

Claude 3 Haiku Long Context benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1190 | #246 of 291, top 85% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Writing & Preference

Claude 3 Haiku Writing & Preference benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1195 | #244 of 297, top 83% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1157 | #248 of 295, top 85% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [EQ-Bench Creative Writing](https://noometry.com/benchmarks/eqbench-creative-writing) | 717 | #108 of 115, top 94% |  | [EQ-Bench](https://eqbench.com/creative_writing.html) |  |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1190 | #241 of 295, top 82% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

## Compare Claude 3 Haiku

-   [Claude 3 Haiku vs DeepSeek-R1-Distill-Qwen-1.5B](https://noometry.com/compare/claude-3-haiku-vs-deepseek-r1-distill-qwen-1-5b)
-   [Claude 3 Haiku vs Gemma 2 9B](https://noometry.com/compare/claude-3-haiku-vs-gemma-2-9b)
-   [Claude 3 Haiku vs Ministral 3B](https://noometry.com/compare/claude-3-haiku-vs-ministral-3b)
-   [Claude 3 Haiku vs Dolly 2.0-12b](https://noometry.com/compare/claude-3-haiku-vs-dolly-2-0-12b)
-   [Claude 3 Haiku vs Mistral Nemo](https://noometry.com/compare/claude-3-haiku-vs-mistral-nemo)
-   [Claude 3 Haiku vs GPT-4o mini](https://noometry.com/compare/claude-3-haiku-vs-gpt-4o-mini)
-   [Claude 3 Haiku vs GPT-6 Astra](https://noometry.com/compare/claude-3-haiku-vs-gpt-6-astra)
-   [Claude 3 Haiku vs Gemini 3.8 Flash](https://noometry.com/compare/claude-3-haiku-vs-gemini-3-8-flash)
-   [Claude 3 Haiku vs Kimi K3](https://noometry.com/compare/claude-3-haiku-vs-kimi-k3)
-   [Claude 3 Haiku vs Grok 4.6](https://noometry.com/compare/claude-3-haiku-vs-grok-4-6)
-   [Claude 3 Haiku vs Qwen3.8 Max](https://noometry.com/compare/claude-3-haiku-vs-qwen3-8-max)
-   [Claude 3 Haiku vs GLM-5.3](https://noometry.com/compare/claude-3-haiku-vs-glm-5-3)
-   [Claude 3 Haiku vs Muse Spark 1.3](https://noometry.com/compare/claude-3-haiku-vs-muse-spark-1-3)
-   [Claude 3 Haiku vs DeepSeek V4 Pro](https://noometry.com/compare/claude-3-haiku-vs-deepseek-v4-pro)

## Other Anthropic models

-   [Claude Fable 5.1](https://noometry.com/models/claude-fable-5-1)69.0
-   [Claude Opus 5.5](https://noometry.com/models/claude-opus-5-5)68.6
-   [Claude Opus 5](https://noometry.com/models/claude-opus-5)67.8
-   [Claude Fable 5](https://noometry.com/models/claude-fable-5)66.8
-   [Claude Sonnet 5.5](https://noometry.com/models/claude-sonnet-5-5)61.9
-   [Claude Opus 4.8](https://noometry.com/models/claude-opus-4-8)60.7
-   [Claude Opus 4.7](https://noometry.com/models/claude-opus-4-7)58.3
-   [Claude Opus 4.6](https://noometry.com/models/claude-opus-4-6)58.2

## Frequently asked questions

### How good is Claude 3 Haiku?

Claude 3 Haiku by Anthropic ranks 340th of 354 ranked models on the Noometry Index as of October 2026, with a score of 25.9. Its strongest category is multimodal, where it ranks 128th.

### Is Claude 3 Haiku open source?

No. Claude 3 Haiku is proprietary and available only through Anthropic's API and partner platforms.

### How fast is Claude 3 Haiku?

Claude 3 Haiku generated about 41 output tokens per second in the Kagi LLM Benchmark's timed runs. Speed varies by provider, load and reasoning effort.

### What are Claude 3 Haiku's strengths and weaknesses?

Relative to other ranked models, Claude 3 Haiku places best in long context, instruction following, multilingual and lowest in multimodal, math, coding.

### What is Claude 3 Haiku best at?

Its best category is multimodal, where it ranks 128th on Noometry.

### Cite this page

Noometry. (2026). Claude 3 Haiku benchmarks and pricing. Retrieved October 10, 2026, from https://noometry.com/models/claude-3-haiku

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/models/claude-3-haiku.md).