Round score
—
p99_e2e_ms_rel_range 16.4692 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 16.4692 exceeds reproducibility bar 0.335
32 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-000 | 93.07ms | 0.215s | 44 | 15.45ms | — |
| hf-001 | 116.39ms | 0.318s | 41 | 102.31ms | — |
| hf-002 | 118.56ms | 0.316s |
verdict
evidence
min logprob
num prompts
mean logprob
coverage ratio
quantile logprob
num positions scored
role
| 41 |
| 103.37ms |
| — |
| hf-003 | 120.85ms | 0.315s | 40 | 103.33ms | — |
| hf-004 | 118.69ms | 0.321s | 41 | 104.70ms | — |
| hf-005 | 120.84ms | 0.337s | 42 | 103.05ms | — |
| hf-006 | 122.41ms | 0.339s | 42 | 102.86ms | — |
| hf-007 | 123.64ms | 0.215s | 29 | 15.61ms | — |
| hf-008 | 107.62ms | 0.183s | 23 | 15.46ms | — |
| hf-009 | 89.23ms | 0.194s | 20 | 16.04ms | — |
| hf-010 | 89.67ms | 0.180s | 28 | 15.24ms | — |
| hf-011 | 88.26ms | 0.400s | 71 | 103.40ms | — |
| hf-012 | 120.10ms | 0.357s | 47 | 104.39ms | — |
| hf-013 | 126.28ms | 0.321s | 40 | 103.35ms | — |
| hf-014 | 127.28ms | 0.342s | 50 | 102.76ms | — |
| hf-015 | 127.86ms | 0.329s | 43 | 102.94ms | — |
| hf-016 | 128.46ms | 0.521s | 70 | 105.33ms | — |
| hf-017 | 131.52ms | 0.606s | 103 | 105.13ms | — |
| hf-018 | 120.90ms | 0.355s | 46 | 103.57ms | — |
| hf-019 | 122.64ms | 0.330s | 42 | 103.14ms | — |
| hf-020 | 129.58ms | 0.208s | 21 | 16.89ms | — |
| hf-021 | 99.00ms | 0.329s | 48 | 102.32ms | — |
| hf-022 | 120.12ms | 0.313s | 40 | 101.89ms | — |
| hf-023 | 113.64ms | 0.204s | 23 | 15.63ms | — |
| hf-024 | 102.17ms | 0.336s | 42 | 105.00ms | — |
| hf-025 | 120.33ms | 0.335s | 42 | 115.42ms | — |
| hf-026 | 134.71ms | 0.320s | 42 | 101.53ms | — |
| hf-027 | 120.24ms | 0.211s | 24 | 15.56ms | — |
| hf-028 | 100.34ms | 0.394s | 56 | 102.53ms | — |
| hf-029 | 115.97ms | 0.349s | 48 | 101.96ms | — |
| hf-030 | 118.12ms | 0.411s | 61 | 101.33ms | — |
| hf-031 | 121.56ms | 0.260s | 42 | 15.67ms | — |
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