Round score
—
p99_e2e_ms_rel_range 0.6179 exceeds reproducibility bar 0.335
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
p99_e2e_ms_rel_range 0.6179 exceeds reproducibility bar 0.335
32 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-000 | 185.92ms | 0.796s | 46 | 221.24ms | — |
| hf-001 | 403.59ms | 0.801s | 42 | 148.06ms | — |
| hf-002 | 208.13ms | 0.617s |
verdict
evidence
min logprob
num prompts
mean logprob
coverage ratio
quantile logprob
num positions scored
role
| 50 |
| 147.87ms |
| — |
| hf-003 | 198.62ms | 0.433s | 41 | 147.47ms | — |
| hf-004 | 189.26ms | 0.232s | 15 | 15.64ms | — |
| hf-005 | 154.74ms | 0.427s | 43 | 154.07ms | — |
| hf-006 | 197.66ms | 0.826s | 49 | 213.41ms | — |
| hf-007 | 398.55ms | 0.853s | 40 | 218.14ms | — |
| hf-008 | 214.04ms | 1.248s | 43 | 218.88ms | — |
| hf-009 | 196.79ms | 1.397s | 43 | 216.56ms | — |
| hf-010 | 472.61ms | 1.635s | 57 | 220.71ms | — |
| hf-011 | 491.89ms | 1.433s | 47 | 212.87ms | — |
| hf-012 | 448.06ms | 1.445s | 42 | 212.91ms | — |
| hf-013 | 459.34ms | 1.034s | 42 | 212.69ms | — |
| hf-014 | 413.18ms | 1.395s | 61 | 212.90ms | — |
| hf-015 | 225.06ms | 0.605s | 18 | 212.70ms | — |
| hf-016 | 406.29ms | 1.450s | 59 | 215.06ms | — |
| hf-017 | 215.91ms | 0.793s | 43 | 213.74ms | — |
| hf-018 | 394.74ms | 0.639s | 41 | 152.99ms | — |
| hf-019 | 210.17ms | 1.378s | 79 | 216.04ms | — |
| hf-020 | 188.67ms | 1.007s | 41 | 215.86ms | — |
| hf-021 | 209.72ms | 1.007s | 42 | 215.95ms | — |
| hf-022 | 467.42ms | 1.490s | 54 | 219.36ms | — |
| hf-023 | 416.09ms | 0.624s | 22 | 148.96ms | — |
| hf-024 | 220.06ms | 1.073s | 49 | 216.77ms | — |
| hf-025 | 198.13ms | 1.050s | 42 | 216.60ms | — |
| hf-026 | 469.68ms | 1.261s | 42 | 219.42ms | — |
| hf-027 | 490.66ms | 1.124s | 56 | 213.52ms | — |
| hf-028 | 449.34ms | 1.165s | 99 | 216.84ms | — |
| hf-029 | 249.32ms | 0.758s | 46 | 226.32ms | — |
| hf-030 | 211.65ms | 0.523s | 41 | 213.30ms | — |
| hf-031 | 261.57ms | 0.371s | 43 | 19.74ms | — |
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