Claude Haiku 5.5: Intelligence, Performance & Price Analysis
Available providers
Model summary
Claude Haiku 5.5 (Max) is amongst the leading models in intelligence and well priced when comparing to other models of similar price. It's also notably slow per task and very verbose. The model supports text and image input, outputs text, and has a 1M tokens context window.
Claude Haiku 5.5 (Max) scores 36 on the Artificial Analysis Intelligence Index, placing it well above average among comparable models (median: 24). When evaluating the Intelligence Index, it generated 298M tokens, which is very verbose in comparison to the median of 107M.
Pricing for Claude Haiku 5.5 (Max) is $0.10 per 1M input tokens (competitively priced, median: $0.24) and $0.50 per 1M output tokens (competitively priced, median: $0.83). On average, it costs $0.41 per task to evaluate Claude Haiku 5.5 (Max) on the Intelligence Index.
At 14.6 minutes per Intelligence Index task, Claude Haiku 5.5 (Max) is notably slow compared with the median of 6.8 minutes for comparable models (lower is better).
| Reasoning | Yes |
|---|---|
| Input modality | Supports: text and image |
| Output modality | Supports: text |
| Context window | 1M ~1500 A4 pages of size 12 Arial font |
Metrics are compared against models of the same class:
- Non-reasoning models → compared only with other non-reasoning models
- Reasoning models → compared across both reasoning and non-reasoning
- Open weights models → compared only with other open weights models of the same size class:
- Tiny: ≤4B parameters
- Small: 4B–40B parameters
- Medium: 40B–150B parameters
- Large: >150B parameters
- Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:
- <$0.15 per 1M tokens
- $0.15–$1 per 1M tokens
- >$1 per 1M tokens
Intelligence
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Intelligence Index vs. Cost per Task
Capability Indexes
Incorporates 5 evaluations: AA-Briefcase v1.1, AA-Omniscience v1.1, HLE-Diamond, AutomationBench-AA, GDP.pdf · Higher is better
Incorporates 4 evaluations: AutomationBench-AA, AA-Briefcase v1.1, AA-Omniscience v1.1, GDP.pdf · Higher is better
Incorporates 5 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, HLE-Diamond, GDP.pdf, AutomationBench-AA · Higher is better
Incorporates 5 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, MLCR-AA, AutomationBench-AA, HLE-Diamond · Higher is better
Incorporates 7 evaluations: AA-Omniscience v1.1, CritPt v2 (Hard Subset), Terminal-Bench-Science 0.1, HLE-Diamond, Terminal-Bench 4.0, FrontierCode-AA 2.0, AA-Briefcase v1.1 · Higher is better
Incorporates 4 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, HLE-Diamond, GDP.pdf · Higher is better
Evaluations
Agentic knowledge work, Elo
Knowledge
1 - hallucination rate
Agentic SaaS workflows
Agentic scientific research workflows in a terminal
Agentic software engineering in open-source repositories
Reasoning & knowledge
Professional document reasoning, All-pass
Agentic coding & terminal use
Physics reasoning
Quantitative analysis on spreadsheets & documents
Legal agentic work, Hallucination-Gated All-Pass Rate
Agentic real-world work tasks, Elo
Agentic interactive 3D experiences, Elo
Product and brand videos designed in code, Elo
Medical long context reasoning
Rich, varied, well-crafted language
Well-structured, scannable, answer-first
Truthful, acknowledges uncertainty, non-sycophantic
Use of filler and generic language
AA-PersonalityBench
Personality Indexes
Cost
Cost per Intelligence Index Task
Cost to Run Artificial Analysis Intelligence Index
Pricing: Cache Hit, Input, and Output
Performance
Measured by time per task (minutes), output speed (tokens per second), time to first answer token and time to first token (seconds)
Time per Intelligence Index Task
Output Speed
Time to First Answer Token
Token Use
Output Tokens per Intelligence Index Task
Context Window
Context Window
Further details
Weights | |||||||||
|---|---|---|---|---|---|---|---|---|---|
| Claude Haiku 5.5 (Max) | 36 | - | 1M | $0.077 | 14.6 | 257 | Not available | ||
| Claude Haiku 5.5 (Xhigh) | 35 | - | 1M | $0.077 | 9.8 | 231 | Not available | ||
| Claude Haiku 5.5 (High) | 30 | - | 1M | $0.077 | 6.5 | 225 | Not available | ||
| Claude Haiku 5.5 (Medium) | 25 | - | 1M | $0.077 | 4.0 | 224 | Not available | ||
| Claude Haiku 5.5 (Low) | 19 | - | 1M | $0.077 | 2.2 | 212 | Not available |
Frequently Asked Questions
Common questions about Claude Haiku 5.5
Claude Haiku 5.5 was released on October 7, 2026.
Claude Haiku 5.5 was created by Anthropic.
Claude Haiku 5.5 has 5 effort levels: max, xhigh, high, medium, and low. Claude Haiku 5.5 scores 36 (max), 35 (xhigh), 30 (high), 25 (medium), and 19 (low) on the Artificial Analysis Intelligence Index. Claude Haiku 5.5 (Max) is well above average among other models in a similar price tier (median: 24).
Claude Haiku 5.5 takes 14.6 minutes (max), 9.8 minutes (xhigh), 6.5 minutes (high), 4.0 minutes (medium), and 2.2 minutes (low) per Intelligence Index task (based on Anthropic's API; lower is better). Claude Haiku 5.5 (Max) is slower than average compared to other models in a similar price tier (median: 6.8 minutes).
Claude Haiku 5.5 has a time to first answer token of 184.31s (max), 48.13s (xhigh), 18.53s (high), 9.71s (medium), and 5.03s (low) (based on Anthropic's API). Claude Haiku 5.5 (Max)'s time to first answer token is at the higher end compared to other models in a similar price tier (median: 8.17s).
Claude Haiku 5.5 costs $0.10 per 1M input tokens (very competitive, median: $0.24) and $0.50 per 1M output tokens (very competitive, median: $0.83), based on Anthropic's API.
Claude Haiku 5.5 costs $0.10 per 1M input tokens and $0.50 per 1M output tokens (based on Anthropic's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.077 per 1M tokens. Pricing may vary by provider. Compare provider pricing
When evaluated on the Intelligence Index, Claude Haiku 5.5 generated 298M output tokens (max), 151M output tokens (xhigh), 89.8M output tokens (high), 52.7M output tokens (medium), and 29.9M output tokens (low). Claude Haiku 5.5 (Max)'s output token count is at the higher end compared to other models in a similar price tier (median: 107M).
Yes, Claude Haiku 5.5 is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
Claude Haiku 5.5 supports text and image input.
Claude Haiku 5.5 supports text output.
Yes, Claude Haiku 5.5 supports image input and can analyze, describe, and answer questions about images.
Yes, Claude Haiku 5.5 is multimodal. It can process text and image input and generate text output.
Claude Haiku 5.5 has a context window of 1M tokens. This determines how much text and conversation history the model can process in a single request.
No, Claude Haiku 5.5 is proprietary. The model weights are not publicly available.
Claude Haiku 5.5 is a proprietary model and Anthropic has not disclosed the model size or parameter count.
Claude Haiku 5.5 achieves a score of 36 (max), 35 (xhigh), 30 (high), 25 (medium), and 19 (low) on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across knowledge work, coding, science, and general knowledge.
Yes, Claude Haiku 5.5 is available via API through 1 provider. Compare API providers
Claude Haiku 5.5 is available through 1 API provider. Compare providers