Create .eval_results/gpqa_diamond.yaml
Browse files
.eval_results/gpqa_diamond.yaml
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: Idavidrein/gpqa
|
| 3 |
+
task_id: diamond
|
| 4 |
+
value: 89.2
|
| 5 |
+
date: "2026-05-07"
|
| 6 |
+
source:
|
| 7 |
+
url: https://huggingface.co/OrionLLM/GRM-2.6-Opus/
|
| 8 |
+
name: Official GRM-2.6-Opus Benchmarks
|
| 9 |
+
user: DedeProGames
|