Round score
—
token logprob at quantile 0.001 is -14.597, 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 -14.597, below -12.0
32 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-000 | 81.86ms | 0.300s | 46 | 70.12ms | — |
| hf-001 | 84.19ms | 0.298s | 48 | 78.06ms | — |
| hf-002 | 104.83ms | 0.284s |
reason
verdict
evidence
min logprob
num prompts
mean logprob
coverage ratio
quantile logprob
num positions scored
| 43 |
| 71.69ms |
| — |
| hf-003 | 101.27ms | 0.317s | 47 | 74.08ms | — |
| hf-004 | 101.75ms | 0.220s | 42 | 17.37ms | — |
| hf-005 | 76.57ms | 0.913s | 133 | 77.42ms | — |
| hf-006 | 97.08ms | 0.289s | 47 | 71.85ms | — |
| hf-007 | 103.13ms | 0.174s | 16 | 18.35ms | — |
| hf-008 | 97.80ms | 0.302s | 43 | 76.08ms | — |
| hf-009 | 94.56ms | 0.290s | 41 | 71.00ms | — |
| hf-010 | 104.72ms | 0.284s | 42 | 72.42ms | — |
| hf-011 | 97.96ms | 0.216s | 41 | 17.91ms | — |
| hf-012 | 71.86ms | 0.380s | 63 | 75.42ms | — |
| hf-013 | 95.57ms | 0.343s | 52 | 82.05ms | — |
| hf-014 | 94.41ms | 0.287s | 42 | 71.07ms | — |
| hf-015 | 89.94ms | 0.387s | 58 | 70.87ms | — |
| hf-016 | 93.84ms | 0.384s | 68 | 72.63ms | — |
| hf-017 | 92.05ms | 0.212s | 41 | 17.88ms | — |
| hf-018 | 81.23ms | 0.148s | 16 | 17.46ms | — |
| hf-019 | 81.50ms | 0.215s | 42 | 17.64ms | — |
| hf-020 | 95.46ms | 0.383s | 71 | 70.58ms | — |
| hf-021 | 96.11ms | 0.773s | 154 | 76.92ms | — |
| hf-022 | 95.36ms | 0.293s | 42 | 70.93ms | — |
| hf-023 | 93.13ms | 0.490s | 75 | 77.18ms | — |
| hf-024 | 98.96ms | 0.309s | 52 | 75.06ms | — |
| hf-025 | 89.95ms | 0.160s | 15 | 18.69ms | — |
| hf-026 | 57.27ms | 0.323s | 45 | 72.90ms | — |
| hf-027 | 85.44ms | 0.312s | 58 | 81.88ms | — |
| hf-028 | 97.63ms | 0.196s | 28 | 17.03ms | — |
| hf-029 | 80.53ms | 0.205s | 42 | 20.91ms | — |
| hf-030 | 73.20ms | 0.281s | 51 | 69.63ms | — |
| hf-031 | 97.11ms | 0.392s | 82 | 18.52ms | — |
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