← All benchmarks
Claude 4.5 Haiku (Non-reasoning)
Anthropic · Released 2025-10-15 · Independent benchmark scores from Artificial Analysis
Intelligence Index
23.7
Output speed
129.1
tokens/sec
Blended price
$2.00
per 1M tokens
Time to first token
0.61s
Model metadata
| Model ID | c2b1e769-7aee-4669-8076-73918bdebf6c |
|---|---|
| Slug | claude-4-5-haiku |
| Release date | 2025-10-15 |
| Provider | Anthropic |
| Provider slug | anthropic |
| Output speed | 129.1 tok/s |
| Time to first token | 0.61s |
| Time to first answer | 0.61s |
| Blended price ($/1M) | $2.00 |
| Input price ($/1M) | $1.00 |
| Output price ($/1M) | $5.00 |
All evaluation scores (17)
| aime | — |
|---|---|
| aime 25 | 39.0% |
| artificial analysis coding index | — |
| artificial analysis intelligence index | 23.70 |
| artificial analysis math index | 39.00 |
| gpqa | 64.6% |
| hle | 4.3% |
| ifbench | 42.0% |
| lcr | 43.7% |
| livecodebench | 51.1% |
| math 500 | — |
| mmlu pro | 80.0% |
| scicode | 34.4% |
| tau banking | — |
| tau2 | 32.5% |
| terminalbench hard | 27.3% |
| terminalbench v2 1 | — |
Source: artificialanalysis.ai/models/claude-4-5-haiku
Benchmark data from Artificial Analysis.