Claude Haiku 5.5
Claude Haiku 5.5 is an API-only (closed weights) language model from Anthropic, released October 7, 2026. The context window is 1M tokens. On the Epoch Capabilities Index it scores 160.4, rank 18 of 256 rated models. API price: $0.1 input / $0.5 output per million tokens.
Introducing Claude Haiku 5.5: the cheapest, fastest, and most capable small model we’ve ever released. Claude Haiku 5.5 is designed for high-volume, cost-sensitive tasks. It reliably handles quick and repetitive workloads (like summaries, compactions, database queries, and classification requests).
Check it against your own PC →
Strengths by category
ModelTape's 0–100 fit on Epoch AI benchmark results.
| Category | Score | Based on |
|---|---|---|
| Reasoning | 25.5 | Chess Puzzles, Mystery Game Puzzles, Humanity's Last Exam |
| Math | 67.4 | ProofBench, OTIS Mock AIME 2024-2025, FrontierMath-Tiers-1-3-v2-Private, FrontierMath-Tier-4-v2-Private |
| Coding | 74.0 | MirrorCode, FrontierSWE |
| Knowledge | 67.8 | GPQA diamond, SimpleQA Verified |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| OTIS Mock AIME | 98.9% |
| GPQA Diamond | 89.8% |
| ProofBench | 89.0% |
| FrontierMath (Tiers 1–3) | 79.0% |
| MirrorCode | 78.9% |
| Chess Puzzles | 52.7% |
| FrontierMath-Tier-4-v2-Private | 46.3% |
| EBR-bench | 43.8% |
| FrontierSWE | 43.8% |
| Humanity's Last Exam | 30.1% |
| Furniture Assembly | 25.0% |
| SimpleQA Verified | 23.8% |
| Mystery Game Puzzles | 22.9% |
Links
Announcement · Epoch AI benchmarks
Models with a similar score
Claude Fable 5 · GPT-6 Sol · GPT-5.6 Sol · GPT-5.5 Pro · Muse Wonder · Kimi K3.1 Pro · GPT-5.6 Terra · GPT-5.4 Pro
More from Anthropic
Claude Fable 5.2 · Claude Sonnet 5.5 · Claude Opus 5.5 · Claude Fable 5.1 · Claude Opus 5 · Claude Sonnet 5 · Claude Fable 5 · Claude Mythos 5