Anthropic model product
Claude Haiku 3
Claude Haiku 3 is an Anthropic LLM designed for fast responses to simple queries and requests.
Updated Sep 8, 2026. Default version: Claude 3 Haiku
LLMBoard Score0.0Claude 3 Haiku
Coverage40%10 benchmark families
Context window200KTokens
Official input priceN/AOfficial price unavailable
Claude Haiku 3 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Claude Haiku 3 Benchmark Results
Benchmark scores for Claude 3 Haiku.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkBIG-Bench Hard | Score73.70% | Rank10 | Participants21 | Percentile55.00% | EvidenceC | Evaluated |
| BenchmarkHellaSwag | Score85.90% | Rank11 | Participants27 | Percentile61.54% | EvidenceC | Evaluated |
| BenchmarkARC-C | Score89.20% | Rank12 | Participants34 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkDROP | Score78.40% | Rank18 | Participants30 | Percentile41.38% | EvidenceC | Evaluated |
| BenchmarkMGSM | Score75.10% | Rank20 | Participants31 | Percentile36.67% | EvidenceC | Evaluated |
| BenchmarkGSM8k | Score88.90% | Rank29 | Participants48 | Percentile40.43% | EvidenceC | Evaluated |
| BenchmarkHumanEval | Score75.90% | Rank48 | Participants66 | Percentile27.69% | EvidenceC | Evaluated |
| BenchmarkMATH | Score38.90% | Rank67 | Participants71 | Percentile5.71% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score75.20% | Rank75 | Participants101 | Percentile26.00% | EvidenceC | Evaluated |
| BenchmarkLM Arena Vision Style Control | Score1,000.63 rating | Rank104 | Participants107 | Percentile2.83% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision | Score950.15 rating | Rank106 | Participants107 | Percentile0.94% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,261.08 rating | Rank196 | Participants210 | Percentile6.70% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,194.46 rating | Rank200 | Participants210 | Percentile4.78% | EvidenceA | Evaluated |
| BenchmarkGPQA | Score33.30% | Rank230 | Participants247 | Percentile6.91% | EvidenceC | Evaluated |
Claude Haiku 3 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision style control | Categorychinese | Rank91 | Rating / score974.52 | Votes1,019 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank92 | Rating / score914.78 | Votes1,019 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank104 | Rating / score1,000.63 | Votes13,380 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank106 | Rating / score948.59 | Votes8,449 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank106 | Rating / score950.15 | Votes13,380 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank106 | Rating / score990.84 | Votes8,449 | ObservationsN/A | Result date |
| Arenatext style control | Categorypolish | Rank143 | Rating / score1,298.36 | Votes264 | ObservationsN/A | Result date |
| Arenatext | Categorypolish | Rank151 | Rating / score1,233.35 | Votes264 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank162 | Rating / score1,208.91 | Votes2,364 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank164 | Rating / score1,171.57 | Votes2,063 | ObservationsN/A | Result date |
| Arenatext style control | Categoryfrench | Rank165 | Rating / score1,276.73 | Votes1,772 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank167 | Rating / score1,102.41 | Votes2,063 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank169 | Rating / score1,108.21 | Votes2,364 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank170 | Rating / score1,246.18 | Votes3,508 | ObservationsN/A | Result date |
| Arenatext | Categoryfrench | Rank171 | Rating / score1,194.39 | Votes1,772 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank175 | Rating / score1,173.40 | Votes3,508 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank175 | Rating / score1,238.59 | Votes1,704 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank176 | Rating / score1,164.75 | Votes1,704 | ObservationsN/A | Result date |
| Arenatext style control | Categorymath | Rank188 | Rating / score1,231.44 | Votes14,983 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry mathematical | Rank189 | Rating / score1,238.69 | Votes13,491 | ObservationsN/A | Result date |
| Arenatext style control | Categoryrussian | Rank189 | Rating / score1,266.68 | Votes11,956 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry medicine and healthcare | Rank191 | Rating / score1,279.36 | Votes6,385 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry mathematical | Rank192 | Rating / score1,187.33 | Votes13,491 | ObservationsN/A | Result date |
| Arenatext | Categorymath | Rank192 | Rating / score1,188.05 | Votes14,983 | ObservationsN/A | Result date |
| Arenatext style control | Categorycoding | Rank193 | Rating / score1,300.90 | Votes20,898 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry writing and literature and language | Rank193 | Rating / score1,245.90 | Votes29,876 | ObservationsN/A | Result date |
| Arenatext style control | Categorymulti turn | Rank193 | Rating / score1,244.57 | Votes19,344 | ObservationsN/A | Result date |
| Arenatext style control | Categorynon english | Rank193 | Rating / score1,245.85 | Votes53,164 | ObservationsN/A | Result date |
| Arenatext style control | Categorychinese | Rank194 | Rating / score1,248.79 | Votes16,707 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexpert | Rank194 | Rating / score1,252.77 | Votes6,336 | ObservationsN/A | Result date |
Claude Haiku 3 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $0.25 input, $1.25 output per 1M via OpenRouter
- Tracked offerings
- 2
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderOpenRouter | Provider model IDanthropic/claude-3-haiku | Regionglobal | Input / 1M$0.25 | Output / 1M$1.25 | Context200K | Updated |
| ProviderHelicone | Provider model IDclaude-3-haiku-20240307 | Regionglobal | Input / 1M$0.25 | Output / 1M$1.25 | Context200K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Claude Haiku 3 Runtime Performance
Provider-specific output speed and catalog latency for Claude 3 Haiku. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderAnthropic | Output Speed100.00 tok/s | Catalog Latency0.50 s | Max Input200K | Max Output200K | Updated |
| ProviderGoogle | Output Speed42.00 tok/s | Catalog Latency0.40 s | Max Input200K | Max Output200K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Claude Haiku 3 Specifications
Technical details for the model's default version.
- Version
- Claude 3 Haiku
- Released
- Mar 13, 2024
- Knowledge cutoff
- Unknown
- Parameters
- N/A
- Context window
- 200K
- Max output
- 200K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Claude Haiku 3 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionClaude 3 Haiku | Released | LLMBoard0.00 | ParametersN/A | Context200K | Max output200K | Open weightsNo | LicenseProprietary |
Models similar to Claude Haiku 3
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AN
Claude Sonnet 3
Anthropic
AN
Claude Haiku 3.5
Anthropic
AN
Claude Opus 3
Anthropic
AN
Claude Sonnet 3.5
Anthropic
AN
Claude Sonnet 3.7
Anthropic
AN
Claude Sonnet 4
Anthropic
What is Claude Haiku 3?
Key information about Claude Haiku 3 and its available data.
Claude Haiku 3 is the fastest and most compact model in Anthropic’s Claude 3 family. It is designed for near-instant responsiveness and answering simple queries and requests.
Data as of 2026-09-08.
FAQ
Common questions about Claude Haiku 3.
When was Claude Haiku 3 released?
Claude Haiku 3's default version was released on Mar 13, 2024.
How much does Claude Haiku 3 cost?
No official standard PAYG price is currently available for Claude Haiku 3. The lowest tracked third-party offer starts at $0.25 input and $1.25 output via OpenRouter.
Who created Claude Haiku 3?
Claude Haiku 3 was created by Anthropic.
What is the context window for Claude Haiku 3?
The default version has a 200K token context window.
Is Claude Haiku 3 open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Claude Haiku 3?
2 provider offerings are linked to the default version.