Round score
—
p99_e2e_ms_rel_range 6.4135 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 6.4135 exceeds reproducibility bar 0.335
32 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-000 | 117.88ms | 0.392s | 48 | 127.58ms | — |
| hf-001 | 146.50ms | 1.202s | 134 | 137.43ms | — |
| hf-002 | 143.14ms | 0.546s |
verdict
evidence
min logprob
num prompts
mean logprob
coverage ratio
quantile logprob
num positions scored
role
| 43 |
| 137.40ms |
| — |
| hf-003 | 156.06ms | 0.535s | 47 | 129.53ms | — |
| hf-004 | 154.37ms | 0.407s | 42 | 128.00ms | — |
| hf-005 | 142.93ms | 0.343s | 21 | 126.07ms | — |
| hf-006 | 142.62ms | 0.407s | 47 | 132.12ms | — |
| hf-007 | 145.53ms | 0.403s | 44 | 126.11ms | — |
| hf-008 | 137.51ms | 0.413s | 43 | 125.21ms | — |
| hf-009 | 148.30ms | 0.409s | 41 | 125.62ms | — |
| hf-010 | 143.06ms | 0.403s | 42 | 127.47ms | — |
| hf-011 | 140.99ms | 0.401s | 41 | 128.22ms | — |
| hf-012 | 154.66ms | 0.395s | 41 | 125.23ms | — |
| hf-013 | 149.26ms | 0.574s | 61 | 127.88ms | — |
| hf-014 | 145.47ms | 0.406s | 42 | 126.73ms | — |
| hf-015 | 142.51ms | 0.514s | 49 | 124.78ms | — |
| hf-016 | 138.91ms | 0.570s | 72 | 126.97ms | — |
| hf-017 | 113.95ms | 1.938s | 184 | 132.25ms | — |
| hf-018 | 146.61ms | 0.401s | 41 | 132.20ms | — |
| hf-019 | 154.76ms | 0.372s | 25 | 127.74ms | — |
| hf-020 | 156.17ms | 0.616s | 71 | 124.50ms | — |
| hf-021 | 152.30ms | 1.207s | 131 | 127.42ms | — |
| hf-022 | 151.41ms | 0.540s | 42 | 127.29ms | — |
| hf-023 | 147.63ms | 0.539s | 47 | 127.27ms | — |
| hf-024 | 152.91ms | 0.575s | 52 | 128.77ms | — |
| hf-025 | 155.98ms | 0.391s | 23 | 128.97ms | — |
| hf-026 | 158.29ms | 0.405s | 42 | 128.21ms | — |
| hf-027 | 149.90ms | 0.392s | 42 | 126.87ms | — |
| hf-028 | 134.20ms | 0.347s | 28 | 127.01ms | — |
| hf-029 | 143.96ms | 0.406s | 42 | 130.33ms | — |
| hf-030 | 142.85ms | 0.400s | 42 | 126.56ms | — |
| hf-031 | 153.93ms | 0.445s | 82 | 17.40ms | — |
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