Qwen3-8B · scored

stock engine (A/A)

reference other judged submitted 10-23 07:59 UTC

Passed every gate.

SpecScore1.006geometric mean of the three speedups

solo1.01× one lane; passes 1.04, 1.01, 1.00

team1.02× team lanes busy; passes 1.02, 1.04, 0.99

busy1.00× KV cache nearly full; passes 1.00, 1.03, 0.98

Lossless gate

what each check is →

Check	Measured	Limit
device memory	162.2 GiB	≤ 165.2 GiB	pass
fixed texts' log-probabilities	0	≤ 0.002	pass
sampled replies' likelihood	+0.0378 ± 0.0803	within ±0.05 at 95%	pass
share of first choices	–	within ±None at 95%	n/a
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	–	1.01
team	–	1.02
busy	–	1.00

Speculator: none
Engine: uploaded with the submission

Everything the judge recorded

{
 "ratios": {
  "solo": {
   "passes": [
    1.040985456606237,
    1.005057585410817,
    1.0000205226173093
   ],
   "ratio": 1.005057585410817
  },
  "team": {
   "passes": [
    1.015036317636797,
    1.03682289049736,
    0.9938355046607794
   ],
   "ratio": 1.015036317636797
  },
  "busy": {
   "passes": [
    0.9975416053689432,
    1.034014997779503,
    0.9818738534693999
   ],
   "ratio": 0.9975416053689432
  }
 },
 "specscore": 1.0058529989596954,
 "greedy_agreement": 1.0,
 "likelihood": {
  "gap": 0.037782875353819634,
  "se": 0.04097148438064572,
  "candidate": -0.6055173907247929,
  "stock": -0.6433002660786126
 },
 "fidelity": 0.0,
 "lengths": {
  "solo": {
   "ratio": 1.0181737103978274,
   "low": 0.6747955816411062,
   "high": 1.3615518391545487
  },
  "team": {
   "ratio": 1.1379842333152081,
   "low": 0.9648401184941504,
   "high": 1.311128348136266
  },
  "busy": {
   "ratio": 1.0166011011385898,
   "low": 0.9078508619045835,
   "high": 1.125351340372596
  }
 },
 "memory": {
  "ok": true,
  "peak_mib": 166112.0,
  "allowed_mib": 169119.1
 },
 "acceptance": {},
 "limits": {
  "greedy_agreement_floor": null,
  "likelihood_bound": 0.05,
  "fidelity_ceiling": 0.002,
  "length_margin": 0.05,
  "memory_slack_mib": 4096
 },
 "reason": null,
 "score": 1.0058529989596954
}