Qwen3-8B · scored
stock engine (A/A)
Passed every gate.
SpecScore0.992geometric mean of the three speedups
solo1.00×
one lane; passes 1.01, 1.00, 1.00
team0.97×
team lanes busy; passes 0.97, 0.99, 0.97
busy1.01×
KV cache nearly full; passes 1.01, 0.97, 1.01
Lossless gate
what each check is →| Check | Measured | Limit | |
|---|---|---|---|
| device memory | 162.0 GiB | ≤ 165.2 GiB | pass |
| fixed texts' log-probabilities | 0 | ≤ 0.002 | pass |
| sampled replies' likelihood | +0.0150 ± 0.0843 | 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 | – | 1.00 |
| team | – | 0.97 |
| busy | – | 1.01 |
Speculator: none
Engine: uploaded with the submission
Everything the judge recorded
{
"ratios": {
"solo": {
"passes": [
1.0144584617868289,
0.9978924136111752,
0.9992205887524143
],
"ratio": 0.9992205887524143
},
"team": {
"passes": [
0.9716311922282856,
0.9899427098354886,
0.9717069663075242
],
"ratio": 0.9717069663075242
},
"busy": {
"passes": [
1.007493850162464,
0.9742815578525859,
1.005364161617695
],
"ratio": 1.005364161617695
}
},
"specscore": 0.9919886352915648,
"greedy_agreement": 1.0,
"likelihood": {
"gap": 0.014981640952985376,
"se": 0.04303021570656583,
"candidate": -0.6816898423267065,
"stock": -0.6966714832796919
},
"argmax": null,
"fidelity": 0.0,
"lengths": {
"solo": {
"ratio": 0.9937437954984385,
"low": 0.6836186044806067,
"high": 1.3038689865162703
},
"team": {
"ratio": 0.878147511482443,
"low": 0.7488790969320821,
"high": 1.007415926032804
},
"busy": {
"ratio": 0.991360959992467,
"low": 0.8808335953247105,
"high": 1.1018883246602234
}
},
"memory": {
"ok": true,
"peak_mib": 165902.0,
"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": 0.9919886352915648
}