Claude Haiku 4.5
Claude Haiku 4.5 is an API-only (closed weights) language model from Anthropic, released October 15, 2025. The context window is 195K tokens. On the Epoch Capabilities Index it scores 142.8, rank 109 of 256 rated models. API price: $1 input / $5 output per million tokens.
Claude Haiku 4.5, our latest small model, is available today to all users. What was recently at the frontier is now cheaper and faster. Five months ago, Claude Sonnet 4 was a state-of-the-art model.
Check it against your own PC →
Strengths by category
ModelTape's 0–100 fit on Epoch AI benchmark results.
| Category | Score | Based on |
|---|---|---|
| Math | 34.1 | MATH level 5, OTIS Mock AIME 2024-2025, FrontierMath-2025-02-28-Private, FrontierMath-Tier-4-2025-07-01-Private |
| Knowledge | 51.7 | GPQA diamond, SimpleQA Verified |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| MATH level 5 | 96.4% |
| OTIS Mock AIME | 66.6% |
| GPQA Diamond | 64.2% |
| Terminal-Bench | 35.5% |
| Balrog | 31.2% |
| SimpleQA Verified | 13.2% |
| FrontierMath-2025-02-28-Private | 10.4% |
| FrontierMath-Tier-4-2025-07-01-Private | 3.5% |
| Chess Puzzles | 3.2% |
Links
Announcement · Epoch AI benchmarks
Models with a similar score
Qwen3.6 27B · GLM-5 · GPT-5.4 Nano · DeepSeek-V3.2 · GPT-5 mini · Gemini 3.5 Flash-Lite · Kimi K2 Thinking · o4-mini
More from Anthropic
Claude Fable 5.2 · Claude Haiku 5.5 · Claude Sonnet 5.5 · Claude Opus 5.5 · Claude Fable 5.1 · Claude Opus 5 · Claude Sonnet 5 · Claude Fable 5