Pinned Loading

1. benchmark-in-a-haystack benchmark-in-a-haystack Public

   Do quality filters pull benchmark questions into pretraining corpora? Injects MMLU, GSM8K, GPQA, ARC, HellaSwag, PIQA and TruthfulQA items into a corpus and ranks them with six quality classifiers,…

   Python

2. tabib-eval tabib-eval Public

   Long-horizon safety evaluation for clinical LLM agents. Simulated hospital environments, decisions graded against a national drug reference. Built on Inspect AI.

   Python

3. thesis thesis Public

   Forked from NathanGodey/thesis

   TeX

4. wargame-evals wargame-evals Public

   LLM safety benchmark for nuclear escalation. The same model recommends a strike in English and refuses in Japanese.

   Python