Latency Benchmarking
by AaaS · open-source · Last verified 2026-03-01
Benchmarks LLM API latency across providers, models, and prompt sizes with detailed statistical analysis. Measures time-to-first-token, inter-token latency, total response time, and generates comparison reports with confidence intervals and percentile distributions.
https://aaas.blog/script/latency-benchmarking ↗C
C—Below Average
Adoption: C+Quality: B+Freshness: ACitations: CEngagement: F
Specifications
- License
- MIT
- Pricing
- open-source
- Capabilities
- ttft-measurement, inter-token-latency, percentile-analysis, multi-provider-comparison, report-generation
- Integrations
- aiohttp, openai, anthropic, numpy
- Use Cases
- provider-comparison, latency-optimization, sla-validation, performance-monitoring
- API Available
- No
- Language
- python
- Dependencies
- aiohttp, openai, anthropic, numpy, matplotlib
- Environment
- Python 3.11+
- Est. Runtime
- 5-20 minutes depending on sample count
- Tags
- script, automation, latency, benchmarking, performance
- Added
- 2026-03-17
- Completeness
- 100%
Index Score
46.1Adoption
50
Quality
78
Freshness
80
Citations
42
Engagement
0