Claude 3.5 Haiku
Anthropic·
LLMssmallcloud
Overview
Fastest model in its intelligence class.
Capabilities and innovations
Low latencyHigh intelligenceTool use
Benchmarks
| Benchmark | Score | Source |
|---|---|---|
| GPQA Diamond | 61.8% | unsourced |
| Humanity’s Last Exam (no tools) | 10.1% | unsourced |
| SWE-bench Verified | 28.7% | unsourced |
| MMLU | 85.9% | unsourced |
- SWE-bench Pro: benchmark did not exist at release
- MMLU-Pro: benchmark did not exist at release
- Terminal-Bench 2.x: benchmark did not exist at release
- MMMU-Pro: benchmark did not exist at release
Links
More from Anthropic
Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.