Round score
—
degenerate output (hf-010: distinct 16-gram ratio 0.013 below baseline 1.000 over 15820 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-010: distinct 16-gram ratio 0.013 below baseline 1.000 over 15820 chars)
32 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-000 | 216.47ms | 1.229s | 44 | 192.01ms | — |
| hf-001 | 424.51ms | 1.832s | 42 | 194.24ms | — |
| hf-002 | 413.62ms | 1.633s |
reason
verdict
evidence
min logprob
num prompts
mean logprob
coverage ratio
quantile logprob
num positions scored
| 50 |
| 194.27ms |
| — |
| hf-003 | 424.24ms | 1.245s | 40 | 191.25ms | — |
| hf-004 | 431.31ms | 1.376s | 43 | 196.16ms | — |
| hf-005 | 417.84ms | 1.621s | 61 | 196.16ms | — |
| hf-006 | 424.19ms | 1.616s | 40 | 193.94ms | — |
| hf-007 | 416.01ms | 1.636s | 56 | 191.75ms | — |
| hf-008 | 246.84ms | 1.434s | 63 | 193.99ms | — |
| hf-009 | 375.83ms | 1.247s | 43 | 202.12ms | — |
| hf-010 | 203.54ms | 19.768s | 5120 | 203.71ms | — |
| hf-011 | 421.79ms | 1.450s | 40 | 204.84ms | — |
| hf-012 | 414.98ms | 1.234s | 41 | 189.82ms | — |
| hf-013 | 257.40ms | 1.420s | 42 | 221.37ms | — |
| hf-014 | 438.84ms | 1.052s | 45 | 188.77ms | — |
| hf-015 | 412.59ms | 1.628s | 46 | 193.29ms | — |
| hf-016 | 487.51ms | 1.427s | 49 | 194.01ms | — |
| hf-017 | 251.43ms | 1.236s | 29 | 199.60ms | — |
| hf-018 | 420.30ms | 2.435s | 96 | 198.16ms | — |
| hf-019 | 251.31ms | 1.627s | 42 | 199.50ms | — |
| hf-020 | 434.32ms | 1.649s | 47 | 196.44ms | — |
| hf-021 | 436.08ms | 1.653s | 43 | 195.44ms | — |
| hf-022 | 416.10ms | 1.441s | 32 | 198.65ms | — |
| hf-023 | 419.37ms | 1.454s | 43 | 199.08ms | — |
| hf-024 | 439.29ms | 1.626s | 40 | 197.76ms | — |
| hf-025 | 435.68ms | 1.556s | 45 | 196.26ms | — |
| hf-026 | 427.79ms | 1.291s | 42 | 195.41ms | — |
| hf-027 | 266.16ms | 1.112s | 43 | 203.51ms | — |
| hf-028 | 438.09ms | 1.046s | 55 | 196.41ms | — |
| hf-029 | 433.12ms | 0.870s | 42 | 193.34ms | — |
| hf-030 | 428.29ms | 0.644s | 42 | 35.18ms | — |
| hf-031 | 295.05ms | 0.448s | 34 | 35.10ms | — |
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