Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...
Tested on 17 benchmarks · BenchGecko score 35.9. Top scores: MATH level 5 (96.4%), OTIS Mock AIME 2024-2025 (66.6%), GPQA diamond (61.6%).
Qwen3 8B scores 36.3 (101% as good) at $0.12/1M input · 88% cheaper
Unusual and adversarial machine learning challenges. Tests robustness of reasoning about edge cases in ML systems.
Complex terminal-based engineering tasks. Models must use command-line tools, navigate filesystems, and debug systems through shell interaction.
Abstraction and Reasoning Corpus. Tests fluid intelligence through novel visual pattern recognition puzzles. Core measure of general intelligence.
ARC-AGI 2, harder sequel to ARC. More complex abstract reasoning patterns that test generalization ability beyond training data.
Competition-level math from AMC, AIME, and olympiad problems. Level 5 is the hardest tier, requiring creative problem-solving.
Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.
Original research-level math problems created by professional mathematicians. Problems are unpublished and cannot be memorized.
- Typemultimodal
- Context200K tokens (~100 books)
- ReleasedOct 2025
- LicenseProprietary
- StatusActive
- Cost / Message~$0.007
Frequently Asked Questions
Key facts · as of 2026-10-05
- Claude Haiku 4.5 by Anthropic. BenchGecko score 35.9, rank 220 of 312 scored models (normalized average of public benchmark scores).
- List price $1.00 input · $5.00 output per 1M tokens (as of 2026-10-05).
- Sold by 8 providers (as of 2026-10-05): Amazon Bedrock $1.00 in / $5.00 out · Anthropic $1.00 in / $5.00 out · Azure $1.00 in / $5.00 out · Google $1.00 in / $5.00 out · Amazon Bedrock $1.10 in / $5.50 out · and 3 more. Every provider
How to cite · data as of 2026-10-05
Claude Haiku 4.5 · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/claude-haiku-4-5
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP