Qwen3.5-27B · scored

stock engine (A/A)

reference other judged submitted 10-23 08:29 UTC

Passed every gate.

SpecScore1.004geometric mean of the three speedups
solo1.00× one lane; passes 1.01, 1.00, 1.00
team1.00× team lanes busy; passes 0.99, 1.04, 1.00
busy1.01× KV cache nearly full; passes 1.01, 1.07, 0.97
CheckMeasuredLimit
device memory163.0 GiB≤ 165.2 GiB pass
fixed texts' log-probabilities0.011≤ 0.02 pass
sampled replies' likelihood+0.0048 ± 0.0488within ±0.05 at 95% pass
share of first choices–within ±0.01 at 95% pass
greedy agreement0.577none on this task n/a
reply lengths–1 ± 0.05 at 95% pass

Speculation

WorkloadTokens / verify stepSpeedup
solo– 1.00
team– 1.00
busy– 1.01

Speculator: none
Engine: uploaded with the submission

Everything the judge recorded
{
 "ratios": {
  "solo": {
   "passes": [
    1.008761488379773,
    1.0005824409016015,
    0.9981717952627063
   ],
   "ratio": 1.0005824409016015
  },
  "team": {
   "passes": [
    0.9927202694227161,
    1.0352933455198303,
    0.9961647098376791
   ],
   "ratio": 0.9961647098376791
  },
  "busy": {
   "passes": [
    1.0139222400802705,
    1.0734747526368411,
    0.9714785094309114
   ],
   "ratio": 1.0139222400802705
  }
 },
 "specscore": 1.0035281504952658,
 "greedy_agreement": 0.5769570663504927,
 "likelihood": {
  "gap": 0.004761770118924591,
  "se": 0.02488099433024719,
  "candidate": -0.4504918456524476,
  "stock": -0.4552536157713722
 },
 "argmax": null,
 "fidelity": 0.011465842514620003,
 "lengths": {
  "solo": {
   "ratio": 1.0,
   "low": 0.48734590354988183,
   "high": 1.512654096450118
  },
  "team": {
   "ratio": 1.0993122978902492,
   "low": 0.7944710496398119,
   "high": 1.4041535461406867
  },
  "busy": {
   "ratio": 0.9427848207877075,
   "low": 0.7096716090888908,
   "high": 1.175898032486524
  }
 },
 "memory": {
  "ok": true,
  "peak_mib": 166906.0,
  "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": 1.0035281504952658
}