Round score
—
degenerate output (hf-015: longest repeated span ratio 0.251 above baseline 0.057 over 674 chars)
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
degenerate output (hf-015: longest repeated span ratio 0.251 above baseline 0.057 over 674 chars)
32 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-000 | 115.30ms | 0.350s | 42 | 109.01ms | — |
| hf-001 | 120.68ms | 0.376s | 42 | 126.04ms | — |
| hf-002 | 141.46ms | 0.377s |
reason
verdict
evidence
min logprob
num prompts
mean logprob
coverage ratio
quantile logprob
num positions scored
| 44 |
| 123.48ms |
| — |
| hf-003 | 136.42ms | 0.398s | 47 | 117.80ms | — |
| hf-004 | 124.48ms | 0.351s | 43 | 108.44ms | — |
| hf-005 | 135.14ms | 0.329s | 28 | 107.86ms | — |
| hf-006 | 126.61ms | 0.373s | 43 | 115.54ms | — |
| hf-007 | 122.36ms | 0.513s | 63 | 109.18ms | — |
| hf-008 | 121.34ms | 0.534s | 61 | 120.08ms | — |
| hf-009 | 126.96ms | 0.584s | 71 | 112.75ms | — |
| hf-010 | 140.94ms | 0.384s | 43 | 110.96ms | — |
| hf-011 | 135.68ms | 0.516s | 55 | 108.97ms | — |
| hf-012 | 118.74ms | 0.375s | 52 | 108.91ms | — |
| hf-013 | 128.91ms | 0.367s | 42 | 109.97ms | — |
| hf-014 | 122.02ms | 0.198s | 21 | 15.74ms | — |
| hf-015 | 97.23ms | 1.560s | 229 | 124.72ms | — |
| hf-016 | 131.72ms | 0.391s | 43 | 111.68ms | — |
| hf-017 | 127.15ms | 0.359s | 43 | 112.40ms | — |
| hf-018 | 127.50ms | 0.371s | 42 | 110.00ms | — |
| hf-019 | 138.67ms | 0.396s | 45 | 108.17ms | — |
| hf-020 | 132.46ms | 0.360s | 43 | 107.16ms | — |
| hf-021 | 127.32ms | 0.369s | 43 | 107.11ms | — |
| hf-022 | 120.81ms | 0.381s | 43 | 109.29ms | — |
| hf-023 | 133.47ms | 0.180s | 15 | 16.12ms | — |
| hf-024 | 106.58ms | 0.332s | 42 | 112.85ms | — |
| hf-025 | 119.01ms | 0.343s | 42 | 107.30ms | — |
| hf-026 | 128.16ms | 0.346s | 43 | 106.78ms | — |
| hf-027 | 126.87ms | 0.217s | 24 | 15.46ms | — |
| hf-028 | 120.40ms | 0.342s | 40 | 110.78ms | — |
| hf-029 | 126.69ms | 0.187s | 18 | 15.76ms | — |
| hf-030 | 88.77ms | 0.338s | 48 | 103.87ms | — |
| hf-031 | 126.51ms | 0.236s | 26 | 15.91ms | — |
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