Round score
—
p99_e2e_ms_rel_range 0.3655 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 0.3655 exceeds reproducibility bar 0.335
32 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-000 | 53.30ms | 0.587s | 42 | 52.62ms | — |
| hf-001 | 63.77ms | 0.654s | 43 | 55.70ms | — |
| hf-002 | 72.64ms | 0.720s |
verdict
evidence
min logprob
num prompts
mean logprob
coverage ratio
quantile logprob
num positions scored
role
| 48 |
| 55.72ms |
| — |
| hf-003 | 67.61ms | 0.590s | 40 | 56.28ms | — |
| hf-004 | 68.14ms | 0.664s | 44 | 52.70ms | — |
| hf-005 | 62.66ms | 0.858s | 56 | 51.93ms | — |
| hf-006 | 64.28ms | 0.655s | 41 | 54.64ms | — |
| hf-007 | 77.02ms | 0.404s | 25 | 54.74ms | — |
| hf-008 | 77.20ms | 0.747s | 51 | 56.60ms | — |
| hf-009 | 60.87ms | 0.725s | 51 | 53.38ms | — |
| hf-010 | 61.22ms | 0.594s | 42 | 53.35ms | — |
| hf-011 | 65.90ms | 0.608s | 42 | 52.80ms | — |
| hf-012 | 68.38ms | 0.659s | 42 | 54.06ms | — |
| hf-013 | 70.81ms | 0.700s | 47 | 52.47ms | — |
| hf-014 | 71.52ms | 0.615s | 43 | 52.83ms | — |
| hf-015 | 63.79ms | 0.593s | 42 | 51.35ms | — |
| hf-016 | 65.01ms | 0.614s | 42 | 51.56ms | — |
| hf-017 | 67.23ms | 0.688s | 44 | 51.94ms | — |
| hf-018 | 86.38ms | 0.373s | 23 | 54.38ms | — |
| hf-019 | 70.37ms | 0.673s | 42 | 52.55ms | — |
| hf-020 | 76.97ms | 0.727s | 48 | 51.51ms | — |
| hf-021 | 76.50ms | 0.875s | 59 | 55.45ms | — |
| hf-022 | 57.80ms | 0.744s | 52 | 55.56ms | — |
| hf-023 | 58.52ms | 0.613s | 43 | 55.81ms | — |
| hf-024 | 74.19ms | 0.603s | 41 | 49.29ms | — |
| hf-025 | 64.48ms | 0.414s | 28 | 48.91ms | — |
| hf-026 | 77.15ms | 0.675s | 45 | 58.77ms | — |
| hf-027 | 66.08ms | 0.875s | 61 | 54.12ms | — |
| hf-028 | 74.61ms | 0.884s | 64 | 50.86ms | — |
| hf-029 | 64.04ms | 0.569s | 40 | 50.72ms | — |
| hf-030 | 65.24ms | 0.845s | 67 | 50.75ms | — |
| hf-031 | 66.52ms | 0.545s | 43 | 12.22ms | — |
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