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