Commit ·
1016dde
1
Parent(s): 2b470a1
Add MathArena evaluation result for aime/aime_2026 (#3)
Browse files- Add MathArena evaluation result for aime/aime_2026 (40c527b455e9f25eb00e6e636ffe75a4cd0b74d8)
Co-authored-by: Jasper <JasperDekoninck@users.noreply.huggingface.co>
.eval_results/MathArena--aime_2026.yaml
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: MathArena/aime_2026
|
| 3 |
+
task_id: MathArena/aime_2026
|
| 4 |
+
value: 82.5
|
| 5 |
+
date: '2026-03-17'
|
| 6 |
+
source:
|
| 7 |
+
url: https://matharena.ai/?comp=aime--aime_2026
|
| 8 |
+
name: Official MathArena Evaluation
|