decision-conformance / clef-flash/hf-fde727a/bnb-nf4-iammrduncan/decide-server-clef-torch-cuda-tf5.19.0-torch2.14.1-cu126 /
2026-10-08-core-greedy-nothink-35cc5e
Checks: 46/49 passed
| Check | Passed | Failures |
|---|---|---|
| invariants | 33/33 | none |
| batched vs separate | 3/6 | support/team: differs by 0.1254 support/needs_human: differs by 0.0773 invoice/disposition: differs by 0.0931 |
| repeat stability | 6/6 | none |
| option order | 2/2 | none |
| monotonic | 2/2 | none |
Run
- Subject
- clef-flash/hf-fde727a/bnb-nf4-iammrduncan/decide-server-clef-torch-cuda-tf5.19.0-torch2.14.1-cu126
- Suite
- decision-conformance · core tier · profile greedy-nothink · mode native
- Items
- 17 succeeded of 17 attempted (17 planned)
- When
- 2026-10-08 21:20:06 UTC · 0 min
- Hardware
- NVIDIA P100 · 16 GB
- Harness
- bench @ 86f9bc0 · scorer bench/decision-conformance 1
- Suite hash
- 554e796a858218e48bcb83da003554769782a4a32d3e061da87510d7f9cea490
- Recipe
- clef-flash/p100/decide · profile nf4 · inference-engines @ e6ceae9
- Latency
- p50 1.65 s · p95 2.29 s · p99 2.29 s (per request)
- Usage
- 5,562 input tokens · 0 output tokens · $0.00
Reproduce
npm run bench -- run --recipe clef-flash/p100/decide \
--recipe-profile nf4 \
--on <host with a p100:p100> \
--suite decision-conformance --tier core --profile greedy-nothinkFiles
exactly as committed under results/