Anthropic model product
Claude Haiku 5.5
5 is an Anthropic large language model for high-volume, cost-sensitive tasks, with text and image input, text output, tool use, and a 1M-token context window.
Updated Oct 23, 2026. Default version: Claude Haiku 5.5
LLMBoard Score80.6Claude Haiku 5.5
Coverage40%27 benchmark families
Context window1MTokens
Official input price$0.10Anthropic API
Claude Haiku 5.5 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Claude Haiku 5.5 Benchmark Results
Benchmark scores for Claude Haiku 5.5.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkMorphology-to-molecule matching | Score25.40% | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkHealthBench | Score61.60% | Rank02 | Participants14 | Percentile92.31% | EvidenceC | Evaluated |
| BenchmarkProgram Bench | Score82.00% | Rank02 | Participants18 | Percentile94.12% | EvidenceC | Evaluated |
| BenchmarkBiomedical image analysis | Score43.50% | Rank02 | Participants2 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkHealthBench Professional (raw) | Score71.00% | Rank02 | Participants2 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkMedicinal Chemistry (ADME) | Score58.00% | Rank02 | Participants2 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkPhysicianBench | Score43.00% | Rank02 | Participants2 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkProtein Design — Library Ranking | Score45.30% | Rank02 | Participants2 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkProtein Design — Sequence Generation | Score33.10% | Rank02 | Participants2 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkProtocols Troubleshooting | Score58.00% | Rank02 | Participants2 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkProtocols Understanding (V2) | Score64.10% | Rank02 | Participants2 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkChartography | Score86.20% | Rank03 | Participants6 | Percentile60.00% | EvidenceC | Evaluated |
| BenchmarkGlobal-MMLU | Score87.80% | Rank03 | Participants8 | Percentile71.43% | EvidenceC | Evaluated |
| BenchmarkLatchBio SingleCellBench | Score56.20% | Rank03 | Participants3 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkLatchBio SpatialBench Verified | Score67.70% | Rank03 | Participants3 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkMILU | Score87.60% | Rank03 | Participants3 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkOfficeQA | Score73.50% | Rank03 | Participants3 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkChartography (no tools) | Score46.40% | Rank03 | Participants3 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkFrontierCode 1.1 (Extended) | Score58.40% | Rank03 | Participants3 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkBenchCAD | Score67.00% | Rank04 | Participants7 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkBenchCAD (with Python tool) | Score87.00% | Rank04 | Participants7 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam (with tools) | Score57.40% | Rank04 | Participants5 | Percentile25.00% | EvidenceC | Evaluated |
| BenchmarkAA-Briefcase v1.1 | Score1,578.00 points | Rank04 | Participants5 | Percentile25.00% | EvidenceC | Evaluated |
| BenchmarkFrontierSWE V2 | Score43.80% | Rank04 | Participants5 | Percentile25.00% | EvidenceC | Evaluated |
| BenchmarkOSWorld 2.1 (strict) | Score37.10% | Rank04 | Participants6 | Percentile40.00% | EvidenceC | Evaluated |
| BenchmarkHealthBench Professional | Score64.80% | Rank05 | Participants20 | Percentile78.95% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam (no tools, text-only) | Score45.90% | Rank05 | Participants14 | Percentile69.23% | EvidenceC | Evaluated |
| BenchmarkSWE-bench Multilingual | Score83.70% | Rank05 | Participants50 | Percentile91.84% | EvidenceC | Evaluated |
| BenchmarkGDPval-AA 2.1 | Score1,620.00 points | Rank05 | Participants6 | Percentile20.00% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Multimodal | Score30.70% | Rank06 | Participants7 | Percentile16.67% | EvidenceC | Evaluated |
Claude Haiku 5.5 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenaagent steerability | Categoryoverall | Rank09 | Rating / score0.05 | VotesN/A | Observations188.6K | Result date |
| Arenaagent bash reliability | Categoryoverall | Rank12 | Rating / score0.07 | VotesN/A | Observations343.3K | Result date |
| Arenaagent bash reliability no prereq | Categoryoverall | Rank13 | Rating / score0.08 | VotesN/A | Observations80K | Result date |
| Arenaagent task outcome explicit | Categoryoverall | Rank17 | Rating / score0.02 | VotesN/A | Observations12.9K | Result date |
| Arenaagent | Categoryoverall | Rank18 | Rating / score0.01 | VotesN/A | Observations3M | Result date |
| Arenawebdev | Categorywebdev-react | Rank21 | Rating / score1,604.76 | Votes2,203 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev-html | Rank22 | Rating / score1,568.85 | Votes449 | ObservationsN/A | Result date |
| Arenawebdev | Categoryoverall | Rank23 | Rating / score1,586.15 | Votes3,514 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev | Rank23 | Rating / score1,586.15 | Votes3,514 | ObservationsN/A | Result date |
| Arenaagent praise complaint | Categoryoverall | Rank26 | Rating / score-0.04 | VotesN/A | Observations6.7K | Result date |
| Arenaagent tool hallucination | Categoryoverall | Rank32 | Rating / score-0.01 | VotesN/A | Observations2.4M | Result date |
Claude Haiku 5.5 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.10 input, $0.50 output per 1M
- Official provider
- Anthropic
- Lowest third-party
- From $0.10 input, $0.50 output per 1M via NanoGPT
- Tracked offerings
- 33
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderNanoGPT | Provider model IDanthropic/claude-haiku-5.5 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context1M | Updated |
| ProviderAnthropic | Provider model IDclaude-haiku-5-5 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context1M | Updated |
| ProviderLLM Gateway | Provider model IDanthropic/claude-haiku-5-5 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context1M | Updated |
| ProviderKilo Gateway | Provider model IDanthropic/claude-haiku-5.5 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context1M | Updated |
| ProviderVenice AI | Provider model IDclaude-haiku-5-5 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context1M | Updated |
| ProviderOpenRouter | Provider model IDanthropic/claude-haiku-5.5 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context1M | Updated |
| ProviderAzure | Provider model IDclaude-haiku-5-5 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context1M | Updated |
| ProviderAzure Cognitive Services | Provider model IDclaude-haiku-5-5 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context1M | Updated |
| ProviderVercel AI Gateway | Provider model IDanthropic/claude-haiku-5.5 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context1M | Updated |
| ProviderVertex (Anthropic) | Provider model IDclaude-haiku-5-5@default | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context1M | Updated |
| ProviderMerge Gateway | Provider model IDanthropic/claude-haiku-5-5 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context1M | Updated |
| ProviderGitHub Copilot | Provider model IDclaude-haiku-5.5 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context1M | Updated |
| ProviderOpenCode Go | Provider model IDclaude-haiku-5-5 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context1M | Updated |
| ProviderEden AI | Provider model IDanthropic/claude-haiku-5-5 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context1M | Updated |
| ProviderOpenCode | Provider model IDclaude-haiku-5-5 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context1M | Updated |
| ProviderRequesty | Provider model IDclaude-haiku-5-5 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context1M | Updated |
| ProviderAmazon Bedrock | Provider model IDanthropic.claude-haiku-5-5 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context1M | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDclaude-haiku-5-5 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context1M | Updated |
| ProviderVivgrid | Provider model IDclaude-haiku-5-5 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context1M | Updated |
| ProviderVertex | Provider model IDclaude-haiku-5-5@default | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context1M | Updated |
| ProviderCrossModel | Provider model IDanthropic/claude-haiku-5-5 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context1M | Updated |
| ProviderOfox | Provider model IDanthropic/claude-haiku-5.5 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context1M | Updated |
| Provider302.AI | Provider model IDclaude-haiku-5-5 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context1M | Updated |
| ProviderNEAR AI Cloud | Provider model IDanthropic/claude-haiku-5-5 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context1M | Updated |
| ProviderCloudflare AI Gateway | Provider model IDanthropic/claude-haiku-5.5 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context1M | Updated |
| ProviderAIHubMix | Provider model IDclaude-haiku-5-5 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context1M | Updated |
| ProviderAI/ML API | Provider model IDanthropic/claude-haiku-5.5 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context1M | Updated |
| ProviderNeon | Provider model IDclaude-haiku-5-5 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context1M | Updated |
| ProviderAixy | Provider model IDanthropic/claude-haiku-5-5 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context1M | Updated |
| ProviderCommandCode | Provider model IDclaude-haiku-5-5 | Regionglobal | Input / 1M$0.10 | Output / 1M$0.50 | Context1M | Updated |
Claude Haiku 5.5 Runtime Performance
Provider-specific output speed and catalog latency for Claude Haiku 5.5. Runtime does not affect the capability score.
No runtime data
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Claude Haiku 5.5 Specifications
Technical details for the model's default version.
- Version
- Claude Haiku 5.5
- Released
- Oct 7, 2026
- Knowledge cutoff
- Jun 1, 2026
- Parameters
- N/A
- Context window
- 1M
- Max output
- 128K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Claude Haiku 5.5 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 Haiku 5.5 | Released | LLMBoard80.56 | ParametersN/A | Context1M | Max output128K | Open weightsNo | LicenseProprietary |
Models similar to Claude Haiku 5.5
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AN
Claude Opus 4.7
Anthropic
AN
Claude Opus 4.8
Anthropic
AN
Claude Sonnet 5
Anthropic
AN
Claude Opus 4.6
Anthropic
AN
Claude Mythos 5.1
Anthropic
AN
Claude Fable 5
Anthropic
What is Claude Haiku 5.5?
Key information about Claude Haiku 5.5 and its available data.
5. It is available through the Claude API as `claude-haiku-5-5`.
Data as of 2026-10-22.
FAQ
Common questions about Claude Haiku 5.5.
When was Claude Haiku 5.5 released?
Claude Haiku 5.5's default version was released on Oct 7, 2026.
How much does Claude Haiku 5.5 cost?
Claude Haiku 5.5's official API price is $0.10 per million input tokens and $0.50 per million output tokens via Anthropic. The lowest tracked third-party offer starts at $0.10 input and $0.50 output via NanoGPT.
Who created Claude Haiku 5.5?
Claude Haiku 5.5 was created by Anthropic.
What is the context window for Claude Haiku 5.5?
The default version has a 1M token context window.
Is Claude Haiku 5.5 open weight?
No. The default version is not marked as having publicly available weights.