Qwen3.5-27B · scored
stock engine (A/A)
Passed every gate.
SpecScore1.022geometric mean of the three speedups
solo1.00×
one lane; passes 1.00, 1.00, 0.99
team1.04×
team lanes busy; passes 0.99, 1.04, 1.05
busy1.02×
KV cache nearly full; passes 0.99, 1.02, 1.03
Lossless gate
what each check is →| Check | Measured | Limit | |
|---|---|---|---|
| device memory | 163.0 GiB | ≤ 165.2 GiB | pass |
| fixed texts' log-probabilities | 1.6e-07 | ≤ 0.02 | pass |
| sampled replies' likelihood | +0.0003 ± 0.0475 | within ±0.05 at 95% | pass |
| share of first choices | -0.0005 ± 0.0117 | 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 | – | 1.00 |
| team | – | 1.04 |
| busy | – | 1.02 |
Speculator: none
Engine: uploaded with the submission
Everything the judge recorded
{
"ratios": {
"solo": {
"passes": [
0.9989657937154824,
1.0004210296413552,
0.9935483491507763
],
"ratio": 0.9989657937154824
},
"team": {
"passes": [
0.9909259616236331,
1.0438264221385478,
1.046066282716205
],
"ratio": 1.0438264221385478
},
"busy": {
"passes": [
0.9856728733332578,
1.0224318217511872,
1.034614351590686
],
"ratio": 1.0224318217511872
}
},
"specscore": 1.021576954115734,
"greedy_agreement": 1.0,
"likelihood": {
"gap": 0.00027490182280093256,
"se": 0.02424384596083253,
"candidate": -0.4553254245833045,
"stock": -0.4556003264061054
},
"argmax": {
"gap": -0.0005241070399384373,
"se": 0.0059856399771547044,
"candidate": 0.12618876840639637,
"stock": 0.1267128754463348
},
"fidelity": 1.624993411439967e-07,
"lengths": {
"solo": {
"ratio": 0.9625262740432282,
"low": 0.6416336494027002,
"high": 1.2834188986837562
},
"team": {
"ratio": 1.0053802241321457,
"low": 0.7079128286556374,
"high": 1.3028476196086538
},
"busy": {
"ratio": 0.9967371760853004,
"low": 0.7205395187350113,
"high": 1.2729348334355897
}
},
"memory": {
"ok": true,
"peak_mib": 166888.0,
"allowed_mib": 169119.1
},
"acceptance": {},
"limits": {
"greedy_agreement_floor": null,
"likelihood_bound": 0.05,
"argmax_bound": 0.01,
"fidelity_ceiling": 0.02,
"length_margin": 0.05,
"memory_slack_mib": 4096
},
"reason": null,
"score": 1.021576954115734
}