Anthropic model product
Claude Haiku 3.5
5 is an Anthropic language model for coding, tool use, reasoning, interactive chatbots, data extraction, and real-time content moderation.
Updated Sep 8, 2026. Default version: Claude 3.5 Haiku
LLMBoard Score7.2Claude 3.5 Haiku
Coverage20%9 benchmark families
Context window200KTokens
Official input priceN/AOfficial price unavailable
Claude Haiku 3.5 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Claude Haiku 3.5 Benchmark Results
Benchmark scores for Claude 3.5 Haiku.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkDROP | Score83.10% | Rank09 | Participants30 | Percentile72.41% | EvidenceC | Evaluated |
| BenchmarkMGSM | Score85.60% | Rank15 | Participants31 | Percentile53.33% | EvidenceC | Evaluated |
| BenchmarkTAU-bench Airline | Score22.80% | Rank22 | Participants23 | Percentile4.55% | EvidenceC | Evaluated |
| BenchmarkTAU-bench Retail | Score51.00% | Rank24 | Participants25 | Percentile4.17% | EvidenceC | Evaluated |
| BenchmarkHumanEval | Score88.10% | Rank25 | Participants66 | Percentile63.08% | EvidenceC | Evaluated |
| BenchmarkMATH | Score69.40% | Rank41 | Participants71 | Percentile42.86% | EvidenceC | Evaluated |
| BenchmarkLM Arena Vision Style Control | Score1,127.04 rating | Rank88 | Participants107 | Percentile17.92% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision | Score1,091.88 rating | Rank90 | Participants107 | Percentile16.04% | EvidenceA | Evaluated |
| BenchmarkSWE-Bench Verified | Score40.60% | Rank104 | Participants113 | Percentile8.04% | EvidenceC | Evaluated |
| BenchmarkMMLU-Pro | Score65.00% | Rank108 | Participants138 | Percentile21.90% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,324.03 rating | Rank165 | Participants210 | Percentile21.53% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,255.01 rating | Rank185 | Participants210 | Percentile11.96% | EvidenceA | Evaluated |
| BenchmarkGPQA | Score41.60% | Rank215 | Participants247 | Percentile13.01% | EvidenceC | Evaluated |
Claude Haiku 3.5 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision | Categoryhomework | Rank79 | Rating / score1,117.43 | Votes213 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhomework | Rank79 | Rating / score1,146.55 | Votes213 | ObservationsN/A | Result date |
| Arenavision style control | Categorydiagram | Rank80 | Rating / score1,132.15 | Votes319 | ObservationsN/A | Result date |
| Arenavision | Categorydiagram | Rank81 | Rating / score1,077.30 | Votes319 | ObservationsN/A | Result date |
| Arenavision | Categoryocr | Rank81 | Rating / score1,089.88 | Votes907 | ObservationsN/A | Result date |
| Arenavision style control | Categoryocr | Rank81 | Rating / score1,130.48 | Votes907 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank88 | Rating / score1,127.04 | Votes1,400 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank90 | Rating / score1,091.88 | Votes1,400 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank92 | Rating / score1,116.94 | Votes652 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank93 | Rating / score1,087.44 | Votes652 | ObservationsN/A | Result date |
| Arenatext style control | Categorypolish | Rank127 | Rating / score1,338.81 | Votes2,712 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank139 | Rating / score1,268.73 | Votes1,206 | ObservationsN/A | Result date |
| Arenatext style control | Categoryfrench | Rank142 | Rating / score1,343.02 | Votes827 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank142 | Rating / score1,311.66 | Votes1,740 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank142 | Rating / score1,242.09 | Votes1,528 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank143 | Rating / score1,332.89 | Votes962 | ObservationsN/A | Result date |
| Arenatext | Categorypolish | Rank145 | Rating / score1,249.34 | Votes2,712 | ObservationsN/A | Result date |
| Arenatext style control | Categorylonger query | Rank148 | Rating / score1,344.62 | Votes10,948 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank149 | Rating / score1,175.03 | Votes1,528 | ObservationsN/A | Result date |
| Arenatext style control | Categorycoding | Rank149 | Rating / score1,385.46 | Votes11,133 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank151 | Rating / score1,303.98 | Votes12,367 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry legal and government | Rank151 | Rating / score1,351.78 | Votes4,230 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank153 | Rating / score1,304.69 | Votes9,817 | ObservationsN/A | Result date |
| Arenatext style control | Categorymulti turn | Rank154 | Rating / score1,327.60 | Votes11,191 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank156 | Rating / score1,172.10 | Votes1,206 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank156 | Rating / score1,260.37 | Votes962 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry software and it services | Rank156 | Rating / score1,364.54 | Votes19,590 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry writing and literature and language | Rank156 | Rating / score1,312.94 | Votes16,796 | ObservationsN/A | Result date |
| Arenatext | Categoryfrench | Rank157 | Rating / score1,262.90 | Votes827 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts english | Rank157 | Rating / score1,354.81 | Votes12,308 | ObservationsN/A | Result date |
Claude Haiku 3.5 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $0.80 input, $4 output per 1M via DigitalOcean
- Tracked offerings
- 4
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderDigitalOcean | Provider model IDanthropic-claude-3.5-haiku | Regionglobal | Input / 1M$0.80 | Output / 1M$4 | Context200K | Updated |
| ProviderZenMux | Provider model IDanthropic/claude-3.5-haiku | Regionglobal | Input / 1M$0.80 | Output / 1M$4 | Context200K | Updated |
| Provider302.AI | Provider model IDclaude-3-5-haiku-20241022 | Regionglobal | Input / 1M$0.80 | Output / 1M$4 | 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 3.5 Runtime Performance
Provider-specific output speed and catalog latency for Claude 3.5 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 Latency0.30 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 3.5 Specifications
Technical details for the model's default version.
- Version
- Claude 3.5 Haiku
- Released
- Oct 22, 2024
- Knowledge cutoff
- Unknown
- Parameters
- N/A
- Context window
- 200K
- Max output
- 200K
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Claude Haiku 3.5 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 3.5 Haiku | Released | LLMBoard7.16 | ParametersN/A | Context200K | Max output200K | Open weightsNo | LicenseProprietary |
Models similar to Claude Haiku 3.5
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AN
Claude Sonnet 3
Anthropic
AN
Claude Haiku 3
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 3.5?
Key information about Claude Haiku 3.5 and its available data.
5 is a language model from Anthropic designed for code completion, interactive chatbots, data extraction, and real-time content moderation. It also supports specialized sub-agent tasks and generating personalized experiences from large data volumes.
Data as of 2026-09-08.
FAQ
Common questions about Claude Haiku 3.5.
When was Claude Haiku 3.5 released?
Claude Haiku 3.5's default version was released on Oct 22, 2024.
How much does Claude Haiku 3.5 cost?
No official standard PAYG price is currently available for Claude Haiku 3.5. The lowest tracked third-party offer starts at $0.80 input and $4 output via DigitalOcean.
Who created Claude Haiku 3.5?
Claude Haiku 3.5 was created by Anthropic.
What is the context window for Claude Haiku 3.5?
The default version has a 200K token context window.
Is Claude Haiku 3.5 open weight?
No. The default version is not marked as having publicly available weights.