Round score
—
token logprob at quantile 0.001 is -22.281, below -12.0
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
token logprob at quantile 0.001 is -22.281, below -12.0
32 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-000 | 191.89ms | 1.029s | 43 | 184.85ms | — |
| hf-001 | 409.54ms | 1.437s | 42 | 187.92ms | — |
| hf-002 | 234.04ms | 1.610s |
reason
verdict
evidence
min logprob
num prompts
mean logprob
coverage ratio
quantile logprob
num positions scored
| 51 |
| 188.54ms |
| — |
| hf-003 | 243.80ms | 1.573s | 49 | 188.85ms | — |
| hf-004 | 411.04ms | 1.399s | 43 | 188.33ms | — |
| hf-005 | 237.60ms | 1.440s | 51 | 188.25ms | — |
| hf-006 | 239.85ms | 1.214s | 48 | 182.46ms | — |
| hf-007 | 238.61ms | 2.047s | 50 | 186.39ms | — |
| hf-008 | 410.22ms | 1.820s | 63 | 186.23ms | — |
| hf-009 | 237.94ms | 1.039s | 43 | 185.28ms | — |
| hf-010 | 436.92ms | 1.417s | 25 | 187.35ms | — |
| hf-011 | 421.03ms | 1.245s | 40 | 185.09ms | — |
| hf-012 | 410.50ms | 1.040s | 28 | 185.84ms | — |
| hf-013 | 239.98ms | 1.199s | 42 | 187.51ms | — |
| hf-014 | 251.37ms | 1.209s | 43 | 187.50ms | — |
| hf-015 | 421.99ms | 1.218s | 41 | 184.23ms | — |
| hf-016 | 248.35ms | 1.231s | 53 | 187.00ms | — |
| hf-017 | 360.39ms | 1.239s | 32 | 220.22ms | — |
| hf-018 | 210.82ms | 2.955s | 127 | 187.67ms | — |
| hf-019 | 235.11ms | 1.611s | 42 | 187.31ms | — |
| hf-020 | 455.09ms | 1.223s | 16 | 185.19ms | — |
| hf-021 | 242.10ms | 1.429s | 44 | 186.37ms | — |
| hf-022 | 244.26ms | 1.245s | 32 | 186.60ms | — |
| hf-023 | 406.30ms | 1.633s | 53 | 190.38ms | — |
| hf-024 | 244.73ms | 1.668s | 51 | 184.51ms | — |
| hf-025 | 407.82ms | 1.511s | 45 | 190.62ms | — |
| hf-026 | 244.03ms | 1.332s | 47 | 188.80ms | — |
| hf-027 | 410.85ms | 1.105s | 42 | 187.37ms | — |
| hf-028 | 420.24ms | 0.912s | 24 | 186.37ms | — |
| hf-029 | 408.10ms | 0.804s | 46 | 187.24ms | — |
| hf-030 | 408.36ms | 0.619s | 42 | 32.94ms | — |
| hf-031 | 257.72ms | 0.492s | 43 | 32.66ms | — |
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