Zleap-AI / SAG-Benchmark
Official benchmark reproduction code for the SAG paper
Why this job: says: benchmark; topics: benchmark
What it does
The companion benchmark repository for the SAG2 paper. SQLite FTS5, BM25 and JEV connect source evidence at query time, with no model calls for indexing.
Get started
git clone https://github.com/Zleap-AI/SAG-Benchmark.git
cd SAG-Benchmark/sag2
uv sync --frozen - Maintenance
- Active
- Last commit 23 days ago
- Stars
- 118
- +65 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 75% of the code
Is it looked after?
- Contributors
- 0
- Last 90 days
- Issues
- None
- No issues filed
- Pull requests
- 8 merged
- 0 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| mlcommons / training | 1,778 | 15 days ago | Apache-2.0 | No downloads |
| sierra-research / tau2-bench | 2,429 | yesterday | MIT | No downloads |
| TristanBilot / mlx-benchmark | 241 | 2 months ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 75%
- C 25%
- Shell <1%
Topics
- rag
- sag
- benchmark
- agent
- vector-search
Project record
- JobEvals and observability
- StatusListed
- Commits4
- Forks19
- Watching1
- Stars in 28 days+72
- CreatedMay 28, 2026
- First seen by usNov 11, 2026
- CheckedNov 11, 2026