Round score
—
token logprob at quantile 0.001 is -18.626, 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 -18.626, below -12.0
32 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-000 | 195.36ms | 1.414s | 43 | 203.56ms | — |
| hf-001 | 441.26ms | 1.647s | 43 | 187.77ms | — |
| hf-002 | 413.35ms | 1.832s |
reason
verdict
evidence
min logprob
num prompts
mean logprob
coverage ratio
quantile logprob
num positions scored
| 52 |
| 200.58ms |
| — |
| hf-003 | 414.35ms | 1.565s | 49 | 187.00ms | — |
| hf-004 | 414.85ms | 1.374s | 43 | 200.51ms | — |
| hf-005 | 412.17ms | 1.436s | 45 | 187.70ms | — |
| hf-006 | 432.77ms | 1.218s | 41 | 188.54ms | — |
| hf-007 | 420.80ms | 1.637s | 60 | 191.24ms | — |
| hf-008 | 501.54ms | 1.619s | 30 | 190.67ms | — |
| hf-009 | 374.54ms | 1.046s | 43 | 185.84ms | — |
| hf-010 | 431.33ms | 1.248s | 24 | 192.20ms | — |
| hf-011 | 425.56ms | 1.412s | 40 | 188.39ms | — |
| hf-012 | 414.85ms | 1.364s | 28 | 195.13ms | — |
| hf-013 | 245.29ms | 1.190s | 25 | 194.51ms | — |
| hf-014 | 431.21ms | 1.448s | 42 | 187.36ms | — |
| hf-015 | 245.59ms | 1.422s | 42 | 193.47ms | — |
| hf-016 | 411.67ms | 1.436s | 55 | 191.49ms | — |
| hf-017 | 362.62ms | 1.227s | 43 | 193.99ms | — |
| hf-018 | 424.74ms | 2.230s | 60 | 198.66ms | — |
| hf-019 | 251.13ms | 1.024s | 17 | 187.66ms | — |
| hf-020 | 420.75ms | 1.044s | 16 | 194.13ms | — |
| hf-021 | 245.13ms | 2.027s | 64 | 191.28ms | — |
| hf-022 | 423.77ms | 1.615s | 40 | 199.24ms | — |
| hf-023 | 248.76ms | 1.437s | 46 | 192.22ms | — |
| hf-024 | 443.65ms | 1.674s | 39 | 189.57ms | — |
| hf-025 | 427.89ms | 1.537s | 42 | 189.86ms | — |
| hf-026 | 411.78ms | 1.491s | 75 | 189.66ms | — |
| hf-027 | 241.16ms | 1.135s | 45 | 188.69ms | — |
| hf-028 | 429.72ms | 1.030s | 51 | 198.26ms | — |
| hf-029 | 426.88ms | 0.830s | 46 | 181.91ms | — |
| hf-030 | 413.06ms | 0.644s | 42 | 33.45ms | — |
| hf-031 | 247.51ms | 0.444s | 42 | 31.24ms | — |
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