ai-twinkle / Eval
High-performance LLM evaluation framework with parallel API calls — up to 17× faster than sequential tools. Supports box, math, and logit-based evaluation.
Why this job: says: llm evaluation, evaluation framework; topics: evaluation
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 2 months ago
- Stars
- 118
- +2 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v2.10.0
- Released 55 days ago
- Built with
- Python
- 92% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 77% closed
- 28 still open
- Pull requests
- 42 merged
- 3 waiting
- Releases
- 21
- 20 in the last year
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| strands-agents / evals | 252 | 4 days ago | Apache-2.0 | No downloads |
| OpenDCAI / One-Eval | 165 | 2 months ago | Apache-2.0 | No downloads |
| georgeguimaraes / tribunal | 119 | 14 days ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 92%
- Jupyter Notebook 4%
- Shell 4%
- Dockerfile <1%
Topics
- eval
- evaluation
- llm
Project record
- JobEvals and observability
- StatusListed
- Commits132
- Forks17
- Watching1
- Stars in 28 days+3
- CreatedMar 31, 2025
- First seen by usNov 7, 2026
- CheckedNov 8, 2026