Round score
—
degenerate output (hf-017: distinct 16-gram ratio 0.062 below baseline 1.000 over 16311 chars)
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
degenerate output (hf-017: distinct 16-gram ratio 0.062 below baseline 1.000 over 16311 chars)
32 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-000 | 92.56ms | 0.315s | 44 | 103.79ms | — |
| hf-001 | 121.54ms | 0.312s | 41 | 75.81ms | — |
| hf-002 | 93.80ms | 0.216s |
reason
verdict
evidence
min logprob
num prompts
mean logprob
coverage ratio
quantile logprob
num positions scored
| 41 |
| 19.32ms |
| — |
| hf-003 | 100.00ms | 0.295s | 42 | 76.44ms | — |
| hf-004 | 107.40ms | 0.321s | 41 | 103.48ms | — |
| hf-005 | 120.59ms | 0.347s | 42 | 104.13ms | — |
| hf-006 | 130.56ms | 0.337s | 42 | 76.17ms | — |
| hf-007 | 102.43ms | 0.206s | 29 | 17.64ms | — |
| hf-008 | 78.72ms | 0.164s | 23 | 17.20ms | — |
| hf-009 | 76.09ms | 0.195s | 20 | 17.16ms | — |
| hf-010 | 81.17ms | 0.183s | 28 | 17.19ms | — |
| hf-011 | 74.49ms | 0.410s | 71 | 103.58ms | — |
| hf-012 | 121.38ms | 0.351s | 47 | 75.90ms | — |
| hf-013 | 98.69ms | 0.219s | 40 | 17.95ms | — |
| hf-014 | 99.95ms | 0.308s | 50 | 77.62ms | — |
| hf-015 | 108.62ms | 0.309s | 42 | 77.09ms | — |
| hf-016 | 94.80ms | 0.288s | 31 | 76.66ms | — |
| hf-017 | 94.88ms | 15.894s | 5120 | 104.66ms | — |
| hf-018 | 101.16ms | 0.336s | 46 | 77.37ms | — |
| hf-019 | 96.61ms | 0.293s | 42 | 77.02ms | — |
| hf-020 | 92.97ms | 0.218s | 42 | 19.92ms | — |
| hf-021 | 100.89ms | 0.326s | 48 | 76.80ms | — |
| hf-022 | 107.42ms | 0.289s | 40 | 76.90ms | — |
| hf-023 | 100.29ms | 0.153s | 16 | 17.73ms | — |
| hf-024 | 111.11ms | 0.316s | 40 | 77.10ms | — |
| hf-025 | 100.05ms | 0.537s | 80 | 104.93ms | — |
| hf-026 | 140.56ms | 0.320s | 42 | 77.36ms | — |
| hf-027 | 101.00ms | 0.407s | 56 | 76.61ms | — |
| hf-028 | 96.74ms | 0.284s | 43 | 76.76ms | — |
| hf-029 | 90.52ms | 0.316s | 48 | 76.45ms | — |
| hf-030 | 97.94ms | 0.383s | 61 | 76.84ms | — |
| hf-031 | 111.61ms | 0.287s | 47 | 18.29ms | — |
role
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