Round score
—
p99_e2e_ms_rel_range 0.7171 exceeds reproducibility bar 0.335
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
p99_e2e_ms_rel_range 0.7171 exceeds reproducibility bar 0.335
32 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-000 | 109.38ms | 0.296s | 42 | 80.38ms | — |
| hf-001 | 104.11ms | 0.290s | 42 | 79.29ms | — |
| hf-002 | 97.54ms | 0.190s |
verdict
evidence
min logprob
num prompts
mean logprob
coverage ratio
quantile logprob
num positions scored
role
| 28 |
| 21.89ms |
| — |
| hf-003 | 93.92ms | 0.327s | 47 | 111.37ms | — |
| hf-004 | 128.15ms | 0.327s | 43 | 103.82ms | — |
| hf-005 | 127.53ms | 0.324s | 27 | 110.21ms | — |
| hf-006 | 120.27ms | 0.351s | 42 | 109.47ms | — |
| hf-007 | 134.50ms | 0.345s | 42 | 109.79ms | — |
| hf-008 | 129.41ms | 0.541s | 60 | 121.93ms | — |
| hf-009 | 124.14ms | 0.389s | 41 | 128.44ms | — |
| hf-010 | 333.14ms | 0.520s | 28 | 107.35ms | — |
| hf-011 | 118.47ms | 0.385s | 67 | 101.27ms | — |
| hf-012 | 119.86ms | 0.342s | 50 | 106.14ms | — |
| hf-013 | 130.01ms | 0.298s | 42 | 81.71ms | — |
| hf-014 | 97.23ms | 0.204s | 42 | 16.00ms | — |
| hf-015 | 77.02ms | 0.198s | 42 | 15.36ms | — |
| hf-016 | 71.21ms | 0.209s | 44 | 15.55ms | — |
| hf-017 | 59.34ms | 0.166s | 43 | 15.37ms | — |
| hf-018 | 61.11ms | 0.173s | 41 | 24.29ms | — |
| hf-019 | 98.54ms | 0.143s | 18 | 15.48ms | — |
| hf-020 | 68.31ms | 0.175s | 43 | 15.56ms | — |
| hf-021 | 75.69ms | 0.212s | 46 | 15.96ms | — |
| hf-022 | 82.92ms | 0.129s | 15 | 15.98ms | — |
| hf-023 | 90.30ms | 0.211s | 43 | 15.77ms | — |
| hf-024 | 72.20ms | 0.179s | 42 | 16.01ms | — |
| hf-025 | 90.02ms | 0.212s | 42 | 15.59ms | — |
| hf-026 | 101.64ms | 0.210s | 43 | 16.17ms | — |
| hf-027 | 102.37ms | 0.178s | 24 | 15.57ms | — |
| hf-028 | 92.36ms | 0.322s | 48 | 101.48ms | — |
| hf-029 | 121.97ms | 0.182s | 18 | 15.60ms | — |
| hf-030 | 88.50ms | 0.165s | 23 | 15.80ms | — |
| hf-031 | 88.03ms | 0.179s | 26 | 15.69ms | — |
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