Round score
—
token logprob at quantile 0.001 is -18.562, 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 -18.562, below -12.0
32 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-000 | 510.17ms | 1.963s | 41 | 245.95ms | — |
| hf-001 | 553.46ms | 2.161s | 42 | 244.24ms | — |
| hf-002 | 587.00ms | 1.960s |
reason
verdict
evidence
min logprob
num prompts
mean logprob
coverage ratio
quantile logprob
num positions scored
| 42 |
| 243.83ms |
| — |
| hf-003 | 631.62ms | 2.714s | 43 | 244.40ms | — |
| hf-004 | 664.81ms | 2.326s | 43 | 295.25ms | — |
| hf-005 | 627.89ms | 2.493s | 43 | 252.84ms | — |
| hf-006 | 679.93ms | 2.451s | 50 | 244.66ms | — |
| hf-007 | 563.36ms | 2.145s | 45 | 250.12ms | — |
| hf-008 | 504.88ms | 2.190s | 43 | 295.29ms | — |
| hf-009 | 563.04ms | 5.021s | 174 | 259.55ms | — |
| hf-010 | 596.97ms | 2.678s | 57 | 254.22ms | — |
| hf-011 | 634.18ms | 2.479s | 46 | 256.05ms | — |
| hf-012 | 669.41ms | 2.515s | 42 | 252.76ms | — |
| hf-013 | 780.19ms | 2.170s | 42 | 249.09ms | — |
| hf-014 | 576.68ms | 2.887s | 61 | 255.60ms | — |
| hf-015 | 627.73ms | 1.272s | 18 | 248.36ms | — |
| hf-016 | 510.07ms | 3.525s | 96 | 251.06ms | — |
| hf-017 | 492.35ms | 3.317s | 80 | 255.18ms | — |
| hf-018 | 536.84ms | 2.488s | 42 | 248.37ms | — |
| hf-019 | 576.11ms | 2.854s | 79 | 250.81ms | — |
| hf-020 | 522.82ms | 1.950s | 43 | 264.88ms | — |
| hf-021 | 672.98ms | 2.402s | 42 | 248.30ms | — |
| hf-022 | 716.93ms | 1.449s | 25 | 246.62ms | — |
| hf-023 | 579.34ms | 1.598s | 22 | 263.62ms | — |
| hf-024 | 624.19ms | 2.179s | 65 | 261.26ms | — |
| hf-025 | 606.69ms | 1.647s | 42 | 252.63ms | — |
| hf-026 | 645.04ms | 1.449s | 23 | 251.96ms | — |
| hf-027 | 683.19ms | 1.337s | 52 | 249.47ms | — |
| hf-028 | 722.42ms | 1.122s | 45 | 253.64ms | — |
| hf-029 | 525.45ms | 1.019s | 45 | 252.57ms | — |
| hf-030 | 577.49ms | 0.736s | 42 | 30.77ms | — |
| hf-031 | 402.43ms | 0.616s | 43 | 97.75ms | — |
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