aobench
https://github.com/mskazemi/aobench
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
not yet supported1 Subscribers
Add a CodeTriage badge to aobench
Help out
- Issues
- [HF-08][P1] Convert reviewed AOBench traces to Hub Session Traces Format (STS) with redaction
- [HF-09][P1] Document and test Hugging Face model evaluation path using existing AOBench adapters
- [HF-10][P1] Integrate Hugging Face docs, discoverability, CI validation and opt-in release automation
- [HF-11][P2] Prototype AOBench as a policy-aware OpenEnv/TRL interactive environment
- [HF-12][P2] Research protocol: disjoint HPC permission training data, SFT/GRPO experiments and anti-contamination evaluation
- [HF-13][P3] Evaluate native Hugging Face Benchmark registration and model .eval_results interoperability
- [HF-14][P1 Release] End-to-end Hub publication QA, security/privacy sign-off, crosslinks and rollout/rollback checklist
- An unknown tool name is scored as an RBAC hard fail, and malformed tool arguments drop the task
- [Result] qwen3.5:9b (Ollama, Q4_K_M, local M2 Pro): 0.561 over 3 runs
- fix: prevent new runs of blocked tasks and quarantine unsupported PERF cases
- Docs
- not yet supported