# Automated MNLP evaluation report

- **Model repo:** [`cs-552-2026-catma/general_knowledge_model`](https://huggingface.co/cs-552-2026-catma/general_knowledge_model)
- **Owner(s):** group **catma**
- **Generated at:** 2026-06-11T06:23:10+00:00 (UTC)
- **Pipeline:** [mnlp-project-ci](https://github.com/eric11eca/mnlp-project-ci)

_This PR is opened automatically by the course CI. It is **non-blocking** — you do not need to merge it. The next nightly run will refresh this file._

## Evaluated checkpoint

- **Commit:** [`381739b`](https://huggingface.co/cs-552-2026-catma/general_knowledge_model/commit/381739bfd0d506028c4782a6fad618c9f4d7e03e)
- **Message:** Upload GK Stage 5 merge-aware DPO checkpoint-500 merged local best 249-290
- **Committed:** 2026-06-04T19:48:25+00:00

## Summary

| Benchmark | Accuracy | Status |
|---|---:|---|
| Math | — | not run |
| Knowledge | 0.4900 | ok |
| Multilingual | — | not run |
| Safety | — | not run |

## Sample completions

_Prompts are intentionally omitted to avoid revealing benchmark contents. For multi-completion problems, only one completion is shown per sample._

### Knowledge

**Correct** (1 shown)

- **reference**: `E`
- **overall** (1/1 completions correct)
- **extracted** (✓): `E`
- **completion**:

    ```text
    \boxed{E}
    ```

**Incorrect** (1 shown)

- **reference**: `B`
- **overall** (0/1 completions correct)
- **extracted** (✗): `C`
- **completion**:

    ```text
    \boxed{C}
    ```