Round score
—
p99_e2e_ms_rel_range 0.4754 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 0.4754 exceeds reproducibility bar 0.335
32 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-000 | 172.51ms | 1.158s | 42 | 128.26ms | — |
| hf-001 | 148.66ms | 1.015s | 43 | 126.64ms | — |
| hf-002 | 153.00ms | 1.176s |
verdict
evidence
min logprob
num prompts
mean logprob
coverage ratio
quantile logprob
num positions scored
role
| 48 |
| 122.33ms |
| — |
| hf-003 | 151.67ms | 0.975s | 39 | 122.89ms | — |
| hf-004 | 150.04ms | 1.017s | 43 | 122.89ms | — |
| hf-005 | 150.39ms | 1.189s | 41 | 204.27ms | — |
| hf-006 | 155.19ms | 1.394s | 50 | 204.01ms | — |
| hf-007 | 153.68ms | 1.568s | 56 | 203.96ms | — |
| hf-008 | 151.66ms | 2.397s | 84 | 205.71ms | — |
| hf-009 | 352.44ms | 1.214s | 42 | 121.99ms | — |
| hf-010 | 157.19ms | 1.144s | 43 | 120.67ms | — |
| hf-011 | 146.07ms | 1.018s | 42 | 121.59ms | — |
| hf-012 | 151.92ms | 1.619s | 59 | 204.45ms | — |
| hf-013 | 155.71ms | 1.384s | 47 | 205.78ms | — |
| hf-014 | 160.38ms | 1.357s | 43 | 204.62ms | — |
| hf-015 | 163.18ms | 1.349s | 42 | 205.34ms | — |
| hf-016 | 351.19ms | 1.827s | 69 | 126.08ms | — |
| hf-017 | 158.24ms | 0.585s | 20 | 124.55ms | — |
| hf-018 | 153.25ms | 1.034s | 42 | 130.15ms | — |
| hf-019 | 161.61ms | 1.150s | 42 | 129.40ms | — |
| hf-020 | 163.14ms | 0.773s | 28 | 124.33ms | — |
| hf-021 | 154.46ms | 1.344s | 52 | 123.95ms | — |
| hf-022 | 158.57ms | 1.143s | 43 | 124.33ms | — |
| hf-023 | 165.30ms | 1.226s | 51 | 124.72ms | — |
| hf-024 | 158.22ms | 1.017s | 40 | 128.39ms | — |
| hf-025 | 152.17ms | 1.354s | 45 | 205.20ms | — |
| hf-026 | 152.45ms | 1.224s | 43 | 204.62ms | — |
| hf-027 | 155.03ms | 1.123s | 43 | 206.72ms | — |
| hf-028 | 150.81ms | 1.009s | 43 | 204.47ms | — |
| hf-029 | 150.64ms | 0.905s | 43 | 206.65ms | — |
| hf-030 | 354.54ms | 0.872s | 50 | 12.40ms | — |
| hf-031 | 160.07ms | 0.603s | 42 | 12.17ms | — |
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