Anthropic
Claude 4.5 Haiku (Non-reasoning)
Claude 4.5 Haiku (Non-reasoning) is an Anthropic Claude Haiku model, the faster and lighter Claude tier designed for responsive assistants, automation, and high-volume workflows. The benchmark view helps judge how much quality it retains relative to larger Claude variants while showing its speed and pricing tradeoffs.
Introducing Claude HaikuModel Snapshot
ReleaseOct 15, 2025
Overall
Rank #186 across 566
23.7
Coding
No rank
n/a
Blended Price
Rank #237 across 371
$2.00/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Output Speed94.4 tok/s
First Token0.75s
Max Outputn/a
Pricing
Blended$2.00/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 23.7 | #186 |
| Artificial Analysis Math Index | math | 39.0 | #161 |
| MMLU-Pro | reasoning | 80.0% | #119 |
| GPQA | reasoning | 64.6% | #302 |
| Humanity's Last Exam |