Entries
5
3 scored · 1 disqualified
Settled in
1h 50m
seated Sep 18, 15:59 UTC
Top score
0.6138
0 is baseline speed
Leader
Changed
won by f4ce3e16…a88ba3
5
| Role | Miner | Patch | Status | Score | Duration | Open |
|---|---|---|---|---|---|---|
| baseline | — | — | scored | 0 score breakdown | — | |
| leader |
| b5af9d1…565c5 |
| scored |
| 0.5984 score breakdown |
| — |
| challenger | 6b1ce3a…355a5 | infra failedsla bench candidate-1 rep 1 had 32 failed request(s): candidate-1/rep1/hf-000: completions timed out for http://172.18.0.2:8000/v1/completions | — score breakdown | — |
| challenger | 10f1c42…fde15 | disqualifieddegenerate output (hf-018: answer: longest repeated span ratio 0.656 at or above harness ceiling over 561 chars) | — score breakdown | — |
| challenger | f4ce3e1…88ba3 | scored | 0.6138 score breakdown | — |
19/19 steps
Setup
4/4Waiting on a provider to hand over a machine.
Installing the harness and shipping the repo.
Fetching the baseline and candidate engine images.
Staging the campaign model onto the pod.
Baseline
2/2Loading weights and waiting for the server to answer.
Incumbent
2/2Loading weights and waiting for the server to answer.
Candidate 1 of 3
2/2Loading weights and waiting for the server to answer.
Candidate 2 of 3
2/2Loading weights and waiting for the server to answer.
Candidate 3 of 3
2/2Loading weights and waiting for the server to answer.
Scorer
2/2Loading weights and waiting for the server to answer.
Drift baseline
2/2Loading weights and waiting for the server to answer.
Teardown
1/1Destroying the pod and its volume.
Full workload replay against the latency gates.
Full workload replay against the latency gates.
Full workload replay against the latency gates.
Full workload replay against the latency gates.
Full workload replay against the latency gates.
The pinned baseline image teacher-forces captured outputs against the campaign thresholds.
Full workload replay against the latency gates.