9 lines
163 B
YAML
9 lines
163 B
YAML
- dataset:
|
|
id: openai/gsm8k
|
|
task_id: gsm8k
|
|
config: main
|
|
split: test
|
|
value: 0.095527
|
|
date: "2026-05-09"
|
|
notes: "greedy, no-tools, local eval"
|