Round score
—
token logprob at quantile 0.001 is -14.157, below -12.0
Prompts scored
0 / 0
median_e2e_speedup
Below tolerance
0
answered too little to score
Zeroed total
0
scored 0.0 without measuring
The round score is the scoring rule applied to the prompts below. Both engines are compared at the same output token count, so a candidate that stops early cannot buy speed by answering less: a prompt under the tolerance bar scores nothing and shows its gate reason.
No prompt scores
token logprob at quantile 0.001 is -14.157, below -12.0
32 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-000 | 80.08ms | 0.207s | 42 | 17.18ms | — |
| hf-001 | 73.18ms | 0.210s | 45 | 15.81ms | — |
| hf-002 | 77.77ms | 0.286s |
reason
verdict
evidence
min logprob
num prompts
mean logprob
coverage ratio
quantile logprob
num positions scored
| 48 |
| 70.36ms |
| — |
| hf-003 | 100.87ms | 0.290s | 47 | 74.01ms | — |
| hf-004 | 90.22ms | 0.212s | 46 | 15.55ms | — |
| hf-005 | 90.93ms | 0.302s | 54 | 71.59ms | — |
| hf-006 | 99.49ms | 0.307s | 46 | 71.85ms | — |
| hf-007 | 96.15ms | 0.291s | 51 | 70.34ms | — |
| hf-008 | 91.76ms | 0.307s | 51 | 72.63ms | — |
| hf-009 | 106.73ms | 0.323s | 47 | 71.75ms | — |
| hf-010 | 92.56ms | 0.215s | 42 | 15.84ms | — |
| hf-011 | 92.94ms | 0.290s | 43 | 71.60ms | — |
| hf-012 | 97.79ms | 0.297s | 48 | 70.78ms | — |
| hf-013 | 96.89ms | 0.320s | 56 | 76.63ms | — |
| hf-014 | 95.35ms | 0.204s | 40 | 16.31ms | — |
| hf-015 | 84.51ms | 0.304s | 63 | 73.68ms | — |
| hf-016 | 89.37ms | 0.346s | 65 | 75.27ms | — |
| hf-017 | 102.71ms | 0.282s | 48 | 71.06ms | — |
| hf-018 | 95.67ms | 0.172s | 27 | 15.91ms | — |
| hf-019 | 62.48ms | 0.184s | 27 | 15.54ms | — |
| hf-020 | 73.82ms | 0.201s | 40 | 17.89ms | — |
| hf-021 | 81.70ms | 0.299s | 50 | 71.75ms | — |
| hf-022 | 83.98ms | 0.206s | 41 | 15.48ms | — |
| hf-023 | 73.71ms | 0.315s | 55 | 80.93ms | — |
| hf-024 | 99.29ms | 0.317s | 46 | 72.57ms | — |
| hf-025 | 86.36ms | 0.296s | 43 | 86.25ms | — |
| hf-026 | 98.21ms | 0.283s | 45 | 77.40ms | — |
| hf-027 | 90.56ms | 0.294s | 53 | 82.09ms | — |
| hf-028 | 101.82ms | 0.342s | 58 | 74.96ms | — |
| hf-029 | 92.90ms | 0.290s | 46 | 71.11ms | — |
| hf-030 | 104.29ms | 0.377s | 53 | 70.52ms | — |
| hf-031 | 99.80ms | 0.224s | 43 | 16.67ms | — |
role
evidence
requests per s
sla goodput ratio
output tokens per s
p99 e2e ms rel range
p99 itl ms rel range
p99 ttft ms rel range
Image digest
Patch hash