Claude Haiku 4.5
Anthropic · Released Oct 1, 2025
$1
Input price / MTok
#12 of 27$5
Output price / MTok
#13 of 27200K
Context window
#22 of 2898
Tokens / sec
#13 of 2173.3
SWE-bench Verified
#8 of 1280.7
AIME 2025
#8 of 1073.2
MMMU
#7 of 850.7
OSWorld
#8 of 8Summary
Claude Haiku 4.5 is a proprietary language model from Anthropic, released on Oct 1, 2025.
At $1 input and $5 output per million tokens, it ranks #12 of 27 for input price, placing it mid-range on input cost.
Its context window of 200K tokens ranks #22 of 28 for context depth in this dataset.
It targets budget, agents workloads.
Throughput is measured at 98 tokens per second (ranked #13 of 21 for throughput).
Fastest Claude model; best for high-volume and real-time tasks.
Benchmarks
| Benchmark | Score | Max | % | Rank | Source |
|---|---|---|---|---|---|
| SWE-bench Verified | 73.3 | 100 | 73.3% | #8/12 | Anthropic (self-reported in launch annou... |
| AIME 2025 | 80.7 | 100 | 80.7% | #8/10 | Anthropic (self-reported in launch bench... |
| MMMU | 73.2 | 100 | 73.2% | #7/8 | DataCamp citing Anthropic official launc... |
| OSWorld | 50.7 | 100 | 50.7% | #8/8 | Anthropic (self-reported in launch annou... |
Similar Models
Compare all 6 modelsModels with the most shared benchmark coverage and closest scores to Claude Haiku 4.5.
Compare Claude Haiku 4.5 side by side
Pre-filled with 5 similar models
Speed source: https://artificialanalysis.ai/models/claude-4-5-haiku