Qwen3-8B · scored

stock engine (A/A)

reference other judged submitted 10-23 09:10 UTC

Passed every gate.

SpecScore1.020geometric mean of the three speedups

solo1.03× one lane; passes 1.04, 1.03, 1.01

team1.03× team lanes busy; passes 1.05, 1.03, 0.89

busy0.99× KV cache nearly full; passes 1.01, 0.97, 0.99

Lossless gate

what each check is →

Check	Measured	Limit
device memory	162.6 GiB	≤ 165.2 GiB	pass
fixed texts' log-probabilities	0	≤ 0.002	pass
sampled replies' likelihood	+0.0106 ± 0.0833	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	–	1.03
team	–	1.03
busy	–	0.99

Speculator: none
Engine: uploaded with the submission

Everything the judge recorded

{
 "ratios": {
  "solo": {
   "passes": [
    1.0386563679786551,
    1.0341938418638714,
    1.0110280842590764
   ],
   "ratio": 1.0341938418638714
  },
  "team": {
   "passes": [
    1.0511023594420101,
    1.0346789011721864,
    0.8916915857479177
   ],
   "ratio": 1.0346789011721864
  },
  "busy": {
   "passes": [
    1.0128152141841258,
    0.9694093233965193,
    0.992286777600862
   ],
   "ratio": 0.992286777600862
  }
 },
 "specscore": 1.0201912201852914,
 "greedy_agreement": 1.0,
 "likelihood": {
  "gap": 0.010620843575156691,
  "se": 0.042516112873642375,
  "candidate": -0.6707218881274893,
  "stock": -0.681342731702646
 },
 "fidelity": 0.0,
 "lengths": {
  "solo": {
   "ratio": 1.0399288981480654,
   "low": 0.752489819654699,
   "high": 1.327367976641432
  },
  "team": {
   "ratio": 1.05820830556278,
   "low": 0.8971534879158966,
   "high": 1.2192631232096636
  },
  "busy": {
   "ratio": 1.000022383472946,
   "low": 0.8882403143773665,
   "high": 1.1118044525685256
  }
 },
 "memory": {
  "ok": true,
  "peak_mib": 166454.0,
  "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": 1.0201912201852914
}