Round score
—
token logprob at quantile 0.001 is -13.125, 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
Request interval
Thinking
The same inputs and output limits apply to every engine. Actual concurrency depends on response duration and engine scheduling.
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 -13.125, below -12.0
32 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-000 | 470.53ms | 2.247s | 43 | 255.92ms | — |
| hf-001 | 484.72ms | 2.906s | 47 | 258.38ms | — |
| hf-002 | 549.12ms | 3.783s |
reason
verdict
evidence
min logprob
num prompts
mean logprob
coverage ratio
quantile logprob
num positions scored
| 81 |
| 220.93ms |
| — |
| hf-003 | 520.17ms | 2.722s | 30 | 256.78ms | — |
| hf-004 | 528.36ms | 2.312s | 42 | 257.26ms | — |
| hf-005 | 584.35ms | 2.110s | 41 | 224.21ms | — |
| hf-006 | 606.28ms | 2.126s | 41 | 220.91ms | — |
| hf-007 | 633.90ms | 2.568s | 43 | 225.21ms | — |
| hf-008 | 644.78ms | 1.937s | 21 | 220.76ms | — |
| hf-009 | 664.88ms | 3.238s | 65 | 221.59ms | — |
| hf-010 | 464.48ms | 3.469s | 54 | 223.30ms | — |
| hf-011 | 480.86ms | 2.133s | 42 | 210.59ms | — |
| hf-012 | 492.60ms | 2.212s | 31 | 223.49ms | — |
| hf-013 | 519.32ms | 2.229s | 43 | 216.67ms | — |
| hf-014 | 524.93ms | 2.458s | 48 | 221.06ms | — |
| hf-015 | 540.68ms | 2.678s | 54 | 226.13ms | — |
| hf-016 | 506.46ms | 3.596s | 119 | 215.50ms | — |
| hf-017 | 564.81ms | 2.218s | 45 | 219.64ms | — |
| hf-018 | 524.21ms | 2.995s | 72 | 211.79ms | — |
| hf-019 | 623.32ms | 2.756s | 52 | 224.69ms | — |
| hf-020 | 535.16ms | 1.933s | 42 | 211.46ms | — |
| hf-021 | 538.92ms | 2.367s | 47 | 212.13ms | — |
| hf-022 | 547.12ms | 2.158s | 46 | 212.29ms | — |
| hf-023 | 555.11ms | 1.971s | 41 | 215.83ms | — |
| hf-024 | 563.43ms | 1.792s | 43 | 213.12ms | — |
| hf-025 | 566.97ms | 1.575s | 28 | 213.46ms | — |
| hf-026 | 526.91ms | 1.509s | 56 | 214.48ms | — |
| hf-027 | 533.86ms | 1.343s | 57 | 211.00ms | — |
| hf-028 | 548.31ms | 1.050s | 27 | 210.83ms | — |
| hf-029 | 552.33ms | 0.867s | 40 | 206.10ms | — |
| hf-030 | 562.65ms | 0.725s | 42 | 22.18ms | — |
| hf-031 | 368.25ms | 0.562s | 46 | 21.41ms | — |
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