Round score
—
degenerate output (hf-017: distinct 16-gram ratio 0.056 below baseline 1.000 over 16682 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-017: distinct 16-gram ratio 0.056 below baseline 1.000 over 16682 chars)
32 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-000 | 92.25ms | 0.316s | 44 | 103.95ms | — |
| hf-001 | 123.14ms | 0.335s | 41 | 103.18ms | — |
| hf-002 | 117.14ms | 0.324s |
reason
verdict
evidence
min logprob
num prompts
mean logprob
coverage ratio
quantile logprob
num positions scored
| 41 |
| 103.72ms |
| — |
| hf-003 | 130.33ms | 0.337s | 42 | 103.25ms | — |
| hf-004 | 124.38ms | 0.309s | 28 | 103.05ms | — |
| hf-005 | 119.35ms | 0.364s | 42 | 103.92ms | — |
| hf-006 | 126.39ms | 0.337s | 28 | 103.54ms | — |
| hf-007 | 121.97ms | 0.332s | 43 | 103.39ms | — |
| hf-008 | 119.19ms | 0.203s | 23 | 17.24ms | — |
| hf-009 | 102.48ms | 0.322s | 21 | 103.72ms | — |
| hf-010 | 128.34ms | 0.314s | 28 | 103.73ms | — |
| hf-011 | 120.64ms | 0.330s | 43 | 103.16ms | — |
| hf-012 | 127.81ms | 0.375s | 47 | 103.98ms | — |
| hf-013 | 125.10ms | 0.351s | 33 | 103.41ms | — |
| hf-014 | 118.86ms | 0.361s | 52 | 103.68ms | — |
| hf-015 | 128.60ms | 0.212s | 23 | 17.50ms | — |
| hf-016 | 104.31ms | 0.331s | 43 | 104.39ms | — |
| hf-017 | 134.31ms | 16.141s | 5120 | 107.52ms | — |
| hf-018 | 124.92ms | 0.335s | 40 | 103.64ms | — |
| hf-019 | 116.98ms | 0.334s | 42 | 104.59ms | — |
| hf-020 | 119.33ms | 0.370s | 47 | 104.48ms | — |
| hf-021 | 118.65ms | 0.221s | 29 | 17.85ms | — |
| hf-022 | 127.74ms | 0.323s | 40 | 104.06ms | — |
| hf-023 | 122.66ms | 0.318s | 28 | 104.57ms | — |
| hf-024 | 117.55ms | 0.346s | 41 | 104.35ms | — |
| hf-025 | 127.90ms | 0.353s | 42 | 103.97ms | — |
| hf-026 | 134.46ms | 0.525s | 70 | 104.44ms | — |
| hf-027 | 117.78ms | 0.406s | 56 | 105.33ms | — |
| hf-028 | 132.64ms | 0.347s | 43 | 103.26ms | — |
| hf-029 | 119.49ms | 0.221s | 29 | 17.41ms | — |
| hf-030 | 131.69ms | 0.377s | 50 | 104.20ms | — |
| hf-031 | 126.57ms | 0.229s | 21 | 17.80ms | — |
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