Model Benchmarking Suite
by AaaS · open-source · Last verified 2026-03-01
Performance benchmarking suite measuring LLM inference throughput, latency percentiles, time-to-first-token, and tokens-per-second under various load patterns. Generates detailed performance reports with charts for capacity planning and SLA validation.
https://aaas.blog/script/model-benchmarking-suite ↗C
C—Below Average
Adoption: C+Quality: AFreshness: ACitations: CEngagement: F
Specifications
- License
- MIT
- Pricing
- open-source
- Capabilities
- throughput-testing, latency-profiling, load-testing, ttft-measurement, report-generation
- Integrations
- aiohttp, openai, anthropic, pandas, matplotlib
- Use Cases
- capacity-planning, sla-validation, performance-regression-testing, infrastructure-sizing
- API Available
- No
- Language
- python
- Dependencies
- aiohttp, openai, anthropic, pandas, matplotlib, numpy
- Environment
- Python 3.11+
- Est. Runtime
- 10-30 minutes depending on load patterns
- Tags
- script, automation, benchmarking, performance, throughput
- Added
- 2026-03-17
- Completeness
- 100%
Index Score
49.1Adoption
54
Quality
80
Freshness
82
Citations
46
Engagement
0