Round score
—
token logprob at quantile 0.001 is -18.342, 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 -18.342, below -12.0
32 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-000 | 112.59ms | 0.218s | 47 | 15.63ms | — |
| hf-001 | 99.92ms | 0.898s | 34 | 126.12ms | — |
| hf-002 | 148.38ms | 0.329s |
reason
verdict
evidence
min logprob
num prompts
mean logprob
coverage ratio
quantile logprob
num positions scored
| 39 |
| 66.87ms |
| — |
| hf-003 | 96.16ms | 0.208s | 40 | 16.43ms | — |
| hf-004 | 88.59ms | 0.294s | 43 | 74.99ms | — |
| hf-005 | 102.33ms | 0.366s | 78 | 77.05ms | — |
| hf-006 | 99.98ms | 0.208s | 51 | 20.53ms | — |
| hf-007 | 82.32ms | 0.206s | 43 | 21.62ms | — |
| hf-008 | 94.58ms | 0.186s | 46 | 16.35ms | — |
| hf-009 | 84.85ms | 0.207s | 43 | 15.91ms | — |
| hf-010 | 120.43ms | 0.211s | 44 | 16.39ms | — |
| hf-011 | 120.92ms | 0.298s | 47 | 77.21ms | — |
| hf-012 | 97.67ms | 0.203s | 47 | 15.25ms | — |
| hf-013 | 111.12ms | 0.216s | 40 | 15.37ms | — |
| hf-014 | 81.83ms | 0.192s | 42 | 21.10ms | — |
| hf-015 | 72.40ms | 0.162s | 30 | 15.22ms | — |
| hf-016 | 65.69ms | 0.185s | 51 | 15.43ms | — |
| hf-017 | 75.23ms | 0.182s | 45 | 16.39ms | — |
| hf-018 | 73.35ms | 0.209s | 48 | 15.96ms | — |
| hf-019 | 92.76ms | 0.200s | 42 | 16.28ms | — |
| hf-020 | 77.85ms | 0.187s | 42 | 16.87ms | — |
| hf-021 | 68.91ms | 0.159s | 49 | 15.37ms | — |
| hf-022 | 114.15ms | 0.277s | 41 | 69.17ms | — |
| hf-023 | 95.76ms | 0.171s | 23 | 15.49ms | — |
| hf-024 | 75.13ms | 0.181s | 40 | 15.65ms | — |
| hf-025 | 74.88ms | 0.166s | 42 | 16.10ms | — |
| hf-026 | 113.86ms | 0.219s | 41 | 15.44ms | — |
| hf-027 | 94.29ms | 0.217s | 50 | 17.51ms | — |
| hf-028 | 91.30ms | 0.169s | 29 | 17.38ms | — |
| hf-029 | 76.86ms | 0.199s | 51 | 15.62ms | — |
| hf-030 | 116.61ms | 0.340s | 51 | 124.73ms | — |
| hf-031 | 148.50ms | 0.238s | 42 | 15.13ms | — |
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