Round score
—
p99_e2e_ms_rel_range 0.7942 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 0.7942 exceeds reproducibility bar 0.335
32 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-000 | 90.02ms | 0.215s | 42 | 16.80ms | — |
| hf-001 | 75.67ms | 0.212s | 45 | 15.49ms | — |
| hf-002 | 96.00ms | 0.319s |
verdict
evidence
min logprob
num prompts
mean logprob
coverage ratio
quantile logprob
num positions scored
role
| 48 |
| 94.79ms |
| — |
| hf-003 | 109.65ms | 0.327s | 47 | 102.25ms | — |
| hf-004 | 111.08ms | 0.312s | 46 | 94.31ms | — |
| hf-005 | 119.13ms | 0.344s | 54 | 94.67ms | — |
| hf-006 | 117.54ms | 0.345s | 46 | 97.04ms | — |
| hf-007 | 113.20ms | 0.325s | 51 | 97.04ms | — |
| hf-008 | 109.40ms | 0.344s | 51 | 99.40ms | — |
| hf-009 | 115.16ms | 0.329s | 47 | 67.74ms | — |
| hf-010 | 93.18ms | 0.215s | 42 | 15.88ms | — |
| hf-011 | 100.73ms | 0.288s | 43 | 69.92ms | — |
| hf-012 | 90.42ms | 0.327s | 48 | 105.80ms | — |
| hf-013 | 126.55ms | 0.368s | 56 | 98.35ms | — |
| hf-014 | 120.72ms | 0.308s | 40 | 94.64ms | — |
| hf-015 | 114.35ms | 0.327s | 63 | 68.11ms | — |
| hf-016 | 80.50ms | 0.358s | 65 | 101.82ms | — |
| hf-017 | 109.94ms | 0.314s | 48 | 96.86ms | — |
| hf-018 | 109.10ms | 0.185s | 27 | 15.55ms | — |
| hf-019 | 58.94ms | 0.180s | 27 | 15.27ms | — |
| hf-020 | 84.02ms | 0.208s | 40 | 17.47ms | — |
| hf-021 | 94.44ms | 0.336s | 50 | 97.08ms | — |
| hf-022 | 120.62ms | 0.289s | 41 | 69.53ms | — |
| hf-023 | 89.29ms | 0.306s | 43 | 95.30ms | — |
| hf-024 | 112.70ms | 0.287s | 41 | 68.47ms | — |
| hf-025 | 93.42ms | 0.321s | 43 | 106.26ms | — |
| hf-026 | 129.76ms | 0.302s | 45 | 74.45ms | — |
| hf-027 | 87.59ms | 0.284s | 53 | 74.88ms | — |
| hf-028 | 57.24ms | 0.314s | 58 | 98.75ms | — |
| hf-029 | 114.21ms | 0.322s | 46 | 94.49ms | — |
| hf-030 | 114.08ms | 0.452s | 67 | 99.74ms | — |
| hf-031 | 115.64ms | 0.238s | 43 | 15.73ms | — |
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