From 88337210811f72d936c8c1406b7282803f3273f0 Mon Sep 17 00:00:00 2001 From: Cherrytest Date: Wed, 11 Mar 2026 12:18:19 +0000 Subject: [PATCH] Add evaluation results for GPQA, HLE (#3) - Add evaluation results for GPQA, HLE (f146d97f42ba9b5b57823a9ab4b4a21422d69d01) Co-authored-by: Nathan Habib (batch 1/1) --- .eval_results/gpqa.yaml | 9 +++++++++ .eval_results/hle.yaml | 9 +++++++++ 2 files changed, 18 insertions(+) create mode 100644 .eval_results/gpqa.yaml create mode 100644 .eval_results/hle.yaml diff --git a/.eval_results/gpqa.yaml b/.eval_results/gpqa.yaml new file mode 100644 index 0000000..ffabbfd --- /dev/null +++ b/.eval_results/gpqa.yaml @@ -0,0 +1,9 @@ +- dataset: + id: Idavidrein/gpqa + task_id: diamond + value: 85.2 + date: '2026-02-13' + source: + url: https://huggingface.co/MiniMaxAI/MiniMax-M2.5 + name: Model Card + user: SaylorTwift diff --git a/.eval_results/hle.yaml b/.eval_results/hle.yaml new file mode 100644 index 0000000..ca9652f --- /dev/null +++ b/.eval_results/hle.yaml @@ -0,0 +1,9 @@ +- dataset: + id: cais/hle + task_id: hle + value: 19.4 + date: '2026-02-13' + source: + url: https://huggingface.co/MiniMaxAI/MiniMax-M2.5 + name: Model Card + user: SaylorTwift