Anthropic model product
5 Haiku is Anthropic's fastest model, delivering advanced coding, tool use, and reasoning capabilities at an accessible price.
Updated Aug 12, 2026. Default version: Claude 3.5 Haiku
Technical details for the model's default version.
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for Claude 3.5 Haiku.
| DROP | 83.1% | 09 | 30 | 72.4% | C | |
| MGSM | 85.6% | 15 | 31 | 53.3% | C | |
| TAU-bench Airline | 22.8% | 22 | 23 | 4.5% | C | |
| TAU-bench Retail | 51.0% | 24 | 25 | 4.2% | C | |
| HumanEval | 88.1% | 25 | 66 | 63.1% | C | |
| MATH | 69.4% | 41 | 71 | 42.9% | C | |
| SWE-Bench Verified | 40.6% | 96 | 105 | 8.7% | C | |
| MMLU-Pro | 65.0% | 100 | 129 | 22.7% | C | |
| GPQA | 41.6% | 202 | 234 | 13.7% | C |
Preference and agent-evaluation results for the default version.
| vision style control | overall | 105 | 1128.4 | 1,406 | N/A | |
| vision | overall | 110 | 1092.7 | 1,406 | N/A | |
| text style control | overall | 226 | 1324.0 | 70,050 | N/A | |
| text | overall | 263 | 1255.3 | 70,050 | N/A |
Provider-specific output speed and catalog latency for Claude 3.5 Haiku. Runtime does not affect the capability score.
| Bedrock | 104 tok/s | 0.5 s | 200K | 200K | |
| Anthropic | 100 tok/s | 0.3 s | 200K | 200K | |
| 42 tok/s | 0.4 s | 200K | 200K |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Official vendor API pricing appears first, followed by individual provider offers.
| 302.AI | claude-3-5-haiku-20241022 | global | $0.80 | $4 | 200K | |
| ZenMux | anthropic/claude-3.5-haiku | global | $0.80 | $4 | 200K | |
| DigitalOcean | anthropic-claude-3.5-haiku | global | $0.80 | $4 | 200K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Available versions of this model. The score column identifies the version used in the overall ranking.
| Claude 3.5 Haiku | 9.3 | N/A | 200K | 8.2K | No | Proprietary |
Key information about Claude Haiku 3.5 and its available data.
5 Haiku is Anthropic's fastest model, delivering advanced coding, tool use, and reasoning capabilities at an accessible price. It excels at user-facing products, specialized sub-agent tasks, and generating personalized experiences from large data volumes.
The model is particularly well-suited for code completions, interactive chatbots, data extraction, and real-time content moderation.
Data as of 2026-08-11.
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Common questions about Claude Haiku 3.5.
Claude Haiku 3.5's default version was released on Oct 22, 2024.
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 302.AI.
Claude Haiku 3.5 was created by Anthropic.
The default version has a 200K token context window.
No. The default version is not marked as having publicly available weights.
4 provider offerings are linked to the default version.
Nearby ranked alternatives include Qwen2.5 Omni 7B, Qwen2 72B, Phi 4.