Qwen3-8B · scored
stock engine (A/A)
Passed every gate.
SpecScore0.994geometric mean of the three speedups
solo0.99×
one lane; passes 0.99, 1.00, 0.98
team1.00×
team lanes busy; passes 1.01, 0.99, 1.00
busy1.00×
KV cache nearly full; passes 1.00, 0.96, 1.00
Lossless gate
what each check is →| Check | Measured | Limit | |
|---|---|---|---|
| device memory | 161.9 GiB | ≤ 165.2 GiB | pass |
| fixed texts' log-probabilities | 0 | ≤ 0.002 | pass |
| sampled replies' likelihood | +0.0181 ± 0.0833 | within ±0.05 at 95% | pass |
| share of first choices | – | within ±0.01 at 95% | pass |
| greedy agreement | 1.000 | none on this task | n/a |
| reply lengths | – | 1 ± 0.05 at 95% | pass |
Speculation
| Workload | Tokens / verify step | Speedup |
|---|---|---|
| solo | – | 0.99 |
| team | – | 1.00 |
| busy | – | 1.00 |
Speculator: none
Engine: uploaded with the submission
Everything the judge recorded
{
"ratios": {
"solo": {
"passes": [
0.9856674691207761,
1.000659073472115,
0.9796375281562127
],
"ratio": 0.9856674691207761
},
"team": {
"passes": [
1.0123666159374491,
0.9895510987507782,
0.9969496417172636
],
"ratio": 0.9969496417172636
},
"busy": {
"passes": [
1.0024663209910396,
0.9626648023278629,
1.0005285499062404
],
"ratio": 1.0005285499062404
}
},
"specscore": 0.9943616741915475,
"greedy_agreement": 1.0,
"likelihood": {
"gap": 0.018089371533563048,
"se": 0.04251844886064804,
"candidate": -0.6722500480561777,
"stock": -0.6903394195897408
},
"argmax": null,
"fidelity": 0.0,
"lengths": {
"solo": {
"ratio": 0.9785869999871006,
"low": 0.7254740332510844,
"high": 1.2316999667231168
},
"team": {
"ratio": 0.9602060127745304,
"low": 0.8311672435778311,
"high": 1.0892447819712296
},
"busy": {
"ratio": 0.9815723781873384,
"low": 0.8719304038486108,
"high": 1.091214352526066
}
},
"memory": {
"ok": true,
"peak_mib": 165782.0,
"allowed_mib": 169119.1
},
"acceptance": {},
"limits": {
"greedy_agreement_floor": null,
"likelihood_bound": 0.05,
"argmax_bound": 0.01,
"fidelity_ceiling": 0.002,
"length_margin": 0.05,
"memory_slack_mib": 4096
},
"reason": null,
"score": 0.9943616741915475
}