diff --git a/.eval_results/MathArena--aime_2026.yaml b/.eval_results/MathArena--aime_2026.yaml new file mode 100644 index 0000000..2750d84 --- /dev/null +++ b/.eval_results/MathArena--aime_2026.yaml @@ -0,0 +1,8 @@ +- dataset: + id: MathArena/aime_2026 + task_id: MathArena/aime_2026 + value: 92.5 + date: '2026-03-17' + source: + url: https://matharena.ai/?comp=aime--aime_2026 + name: Official MathArena Evaluation