Files
sakthai-context-1.5b-merged-v2/.eval_results/sakthai-bench-v2.yaml

15 lines
263 B
YAML
Raw Normal View History

task:
- text-generation
dataset:
- sakthai-bench-v2
metrics:
- selection: 34.9
name: Selection Accuracy
verified: true
- arguments: 44.2
name: Arguments Accuracy
verified: true
- strict: 34.2
name: Strict Accuracy
verified: true