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 "Distributed Trace Summary", and done to true. Summarize distributed trace spans into bottlenecks, downstream dependencies, and remediation ideas.
{
"metrics": {
"complete": {
"checks": [
{
"contains": [
"benchmark"
]
},
{
"contains": [
"distributed trace"
]
},
{
"contains": [
"done"
]
}
]
}
}
}temperature
0
max_tokens
520
timeout (s)
60
type
throughput
file
speed-distributed-trace-summary.json