From 6f750b1dbb04059c5082c054b517d757f0741132 Mon Sep 17 00:00:00 2001 From: Nathan Habib Date: Mon, 2 Mar 2026 13:31:44 +0000 Subject: [PATCH] Add MMLU-Pro evaluation result --- .eval_results/mmlu_pro.yaml | 8 ++++++++ 1 file changed, 8 insertions(+) create mode 100644 .eval_results/mmlu_pro.yaml diff --git a/.eval_results/mmlu_pro.yaml b/.eval_results/mmlu_pro.yaml new file mode 100644 index 0000000..3542341 --- /dev/null +++ b/.eval_results/mmlu_pro.yaml @@ -0,0 +1,8 @@ +- dataset: + id: TIGER-Lab/MMLU-Pro + task_id: mmlu_pro + value: 82.5 + source: + url: https://huggingface.co/Qwen/Qwen3.5-9B + name: Model Card + user: SaylorTwift