Round score
—
degenerate output (hf-017: distinct 16-gram ratio 0.144 below baseline 1.000 over 16606 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 0.144 below baseline 1.000 over 16606 chars)
32 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-000 | 91.67ms | 0.316s | 44 | 104.79ms | — |
| hf-001 | 123.40ms | 0.314s | 41 | 75.56ms | — |
| hf-002 | 96.11ms | 0.219s |
reason
verdict
evidence
min logprob
num prompts
mean logprob
coverage ratio
quantile logprob
num positions scored
| 41 |
| 19.43ms |
| — |
| hf-003 | 114.02ms | 0.289s | 40 | 76.77ms | — |
| hf-004 | 100.67ms | 0.323s | 41 | 103.48ms | — |
| hf-005 | 129.79ms | 0.358s | 42 | 102.96ms | — |
| hf-006 | 123.47ms | 0.331s | 42 | 75.83ms | — |
| hf-007 | 106.61ms | 0.209s | 29 | 17.68ms | — |
| hf-008 | 80.46ms | 0.166s | 23 | 17.24ms | — |
| hf-009 | 76.21ms | 0.195s | 20 | 17.14ms | — |
| hf-010 | 82.23ms | 0.184s | 28 | 17.46ms | — |
| hf-011 | 74.76ms | 0.411s | 71 | 103.54ms | — |
| hf-012 | 121.27ms | 0.353s | 47 | 76.12ms | — |
| hf-013 | 100.04ms | 0.220s | 40 | 17.57ms | — |
| hf-014 | 101.00ms | 0.329s | 50 | 102.59ms | — |
| hf-015 | 129.07ms | 0.309s | 43 | 76.13ms | — |
| hf-016 | 93.90ms | 0.287s | 31 | 76.69ms | — |
| hf-017 | 93.65ms | 15.825s | 5120 | 117.46ms | — |
| hf-018 | 117.44ms | 0.368s | 46 | 106.16ms | — |
| hf-019 | 129.36ms | 0.322s | 42 | 76.43ms | — |
| hf-020 | 104.25ms | 0.288s | 42 | 76.55ms | — |
| hf-021 | 94.64ms | 0.319s | 48 | 76.15ms | — |
| hf-022 | 101.07ms | 0.283s | 40 | 76.46ms | — |
| hf-023 | 100.53ms | 0.153s | 16 | 17.65ms | — |
| hf-024 | 122.88ms | 0.351s | 40 | 102.82ms | — |
| hf-025 | 131.55ms | 0.356s | 42 | 103.72ms | — |
| hf-026 | 141.01ms | 0.316s | 42 | 76.31ms | — |
| hf-027 | 98.86ms | 0.202s | 29 | 17.41ms | — |
| hf-028 | 130.94ms | 0.367s | 49 | 76.66ms | — |
| hf-029 | 98.19ms | 0.326s | 48 | 76.21ms | — |
| hf-030 | 107.27ms | 0.409s | 61 | 103.39ms | — |
| hf-031 | 122.42ms | 0.295s | 47 | 17.88ms | — |
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