decision-conformance / d1-3b/hf-051bcc4/bf16-liquidai/decide-server-d1-torch-mps-tf5.19.0-torch2.14.1 /

2026-10-08-core-greedy-nothink-36b01e

Checks: 49/49 passed

CheckPassedFailures
invariants33/33none
batched vs separate6/6none
repeat stability6/6none
option order2/2none
monotonic2/2none

Run

Suite
decision-conformance · core tier · profile greedy-nothink · mode native
Items
17 succeeded of 17 attempted (17 planned)
When
2026-10-08 19:28:10 UTC · 0 min
Hardware
Apple M4 Pro · 24 GB
Harness
bench @ 6498c02 · scorer bench/decision-conformance 1
Suite hash
554e796a858218e48bcb83da003554769782a4a32d3e061da87510d7f9cea490
Recipe
d1-3b/apple-m/decide · profile bf16 · inference-engines @ 6490e6f
Latency
p50 353 ms · p95 572 ms · p99 572 ms (per request)
Usage
3,355 input tokens · 0 output tokens · $0.00

Reproduce

npm run bench -- run --recipe d1-3b/apple-m/decide \
    --recipe-profile bf16 \
    --on <host with a apple-m:m4-pro> \
    --suite decision-conformance --tier core --profile greedy-nothink

Files

exactly as committed under results/