Test fixture
Throughput and TTFT-focused generation tasks.
The model receives the prompt (and optional system message). The run uses scorer rubric_json_metrics with the JSON configuration below. Pass/fail and partial credit are determined entirely by that scorer against the model output; no human grading.
Return JSON only with keys benchmark, title, items, done. Set benchmark to "speed", title to "User Story Set", and done to true. Generate user stories with acceptance criteria for account security settings.
{
"metrics": {
"complete": {
"checks": [
{
"contains": [
"benchmark"
]
},
{
"contains": [
"user stories"
]
},
{
"contains": [
"done"
]
}
]
}
}
}temperature
0
max_tokens
380
timeout (s)
60
type
throughput
file
speed-user-story-set.json