Entries
7
5 scored · 1 disqualified
Settled in
3h 23m
seated Sep 22, 13:08 UTC
Top score
0.6272
0 is baseline speed
Leader
Changed
won by 6b23883d…b2b461
7
| Role | Miner | Patch | Status | Score | Duration | Open |
|---|---|---|---|---|---|---|
| baseline | — | — | scored | 0 score breakdown | — | |
| leader |
| a06ebe5…229eb |
| disqualifieddegenerate output (baseline-relative repetition failures exceed allowance of 4 prompts (hf-029: distinct 16-gram ratio 0.537 is more than 0.10 below baseline 0.652 over 20210 chars)) |
| — score breakdown |
| — |
| challenger | 2d09465…99e48 | scored | -4.8246 score breakdown | — |
| challenger | 3bc8cae…aaad9 | scored | 0.1951 score breakdown | — |
| challenger | b880a79…6664c | scored | -1.9084 score breakdown | — |
| challenger | a246f46…fa30a | infra failedSGLang speculation requires resolved token reservations | — score breakdown | — |
| challenger | 6b23883…2b461 | scored | 0.6272 score breakdown | — |
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.
Second 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 5
2/2Loading weights and waiting for the server to answer.
Candidate 2 of 5
2/2Loading weights and waiting for the server to answer.
Candidate 3 of 5
2/2Loading weights and waiting for the server to answer.
Candidate 4 of 5
2/2Loading weights and waiting for the server to answer.
Candidate 5 of 5
2/2Loading weights and waiting for the server to answer.
Scorer
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.
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.