Add GPQA Diamond evaluation result
This commit is contained in:
parent
92725404d2
commit
7daa976d0c
8
.eval_results/gpqa.yaml
Normal file
8
.eval_results/gpqa.yaml
Normal file
@ -0,0 +1,8 @@
|
|||||||
|
- dataset:
|
||||||
|
id: Idavidrein/gpqa
|
||||||
|
task_id: diamond
|
||||||
|
value: 81.7
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/Qwen/Qwen3.5-9B
|
||||||
|
name: Model Card
|
||||||
|
user: SaylorTwift
|
||||||
Loading…
Reference in New Issue
Block a user