Entries
7
4 scored · 1 disqualified
Settled in
3h 15m
seated Sep 03, 06:56 UTC
Top score
0.7194
0 is baseline speed
Leader
Changed
won by ab2d51b7…c8b457
23/23 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.
Full workload replay against the latency gates.
Incumbent
2/2Loading weights and waiting for the server to answer.
Full workload replay against the latency gates.
Candidate 1 of 5
2/2Loading weights and waiting for the server to answer.
Full workload replay against the latency gates.
Candidate 2 of 5
2/2Loading weights and waiting for the server to answer.
Full workload replay against the latency gates.
Candidate 3 of 5
2/2Loading weights and waiting for the server to answer.
Full workload replay against the latency gates.
Candidate 4 of 5
2/2Loading weights and waiting for the server to answer.
Full workload replay against the latency gates.
Candidate 5 of 5
2/2Loading weights and waiting for the server to answer.
Full workload replay against the latency gates.
Scorer
2/2Loading weights and waiting for the server to answer.
The pinned baseline image teacher-forces captured outputs against the campaign thresholds.
Drift baseline
2/2Loading weights and waiting for the server to answer.
Full workload replay against the latency gates.
Teardown
1/1Destroying the pod and its volume.
7
| Role | Miner | Patch | Status | Score | Duration | Open |
|---|---|---|---|---|---|---|
| baseline | — | — | scored | 0 score breakdown | — | |
| leader | cd6ae37…28b67 | scored | 0.302 score breakdown | — | ||
| challenger | 964c25c…706fc | scored | 0.6461 score breakdown | — | ||
| challenger | ab2d51b…8b457 | scored | 0.7194 score breakdown | — | ||
| challenger | 85d6314…6de95 | infra failedsla bench candidate-3 rep 3 had 5 failed request(s): candidate-3/rep3/hf-019: completions stream from http://172.18.0.2:8000/v1/completions: completion tokens=79 but only 77 inter-token gap(s) (expected at least 78; coalesced stream) | — score breakdown | — | ||
| challenger | c062266…69fac | infra failedp99 e2e ms rel range 0.6179 exceeds reproducibility bar 0.335 | — score breakdown | — | ||
| challenger | d508830…8cd72 | disqualifiedtoken logprob at quantile 0.001 is -18.562, below -12.0 | — score breakdown | — |