Round score
—
degenerate output (hf-023: distinct 16-gram ratio 0.010 below baseline 1.000 over 28339 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-023: distinct 16-gram ratio 0.010 below baseline 1.000 over 28339 chars)
32 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-000 | 70.18ms | 0.203s | 44 | 17.28ms | — |
| hf-001 | 75.06ms | 0.207s | 41 | 17.29ms | — |
| hf-002 | 87.88ms | 0.210s |
reason
verdict
evidence
min logprob
num prompts
mean logprob
coverage ratio
quantile logprob
num positions scored
| 41 |
| 19.46ms |
| — |
| hf-003 | 76.90ms | 0.210s | 43 | 17.43ms | — |
| hf-004 | 76.88ms | 0.159s | 15 | 17.05ms | — |
| hf-005 | 63.60ms | 0.213s | 42 | 17.03ms | — |
| hf-006 | 79.40ms | 0.298s | 47 | 75.20ms | — |
| hf-007 | 96.62ms | 0.199s | 29 | 17.24ms | — |
| hf-008 | 75.06ms | 0.160s | 23 | 17.07ms | — |
| hf-009 | 62.28ms | 0.161s | 21 | 17.13ms | — |
| hf-010 | 62.31ms | 0.161s | 28 | 16.89ms | — |
| hf-011 | 74.78ms | 0.379s | 71 | 75.72ms | — |
| hf-012 | 93.98ms | 0.310s | 47 | 74.79ms | — |
| hf-013 | 94.21ms | 0.313s | 47 | 100.88ms | — |
| hf-014 | 121.56ms | 0.296s | 28 | 74.63ms | — |
| hf-015 | 102.15ms | 0.295s | 44 | 76.78ms | — |
| hf-016 | 101.02ms | 0.293s | 31 | 75.97ms | — |
| hf-017 | 99.31ms | 0.330s | 56 | 75.45ms | — |
| hf-018 | 95.76ms | 0.310s | 46 | 76.16ms | — |
| hf-019 | 97.40ms | 0.289s | 42 | 75.81ms | — |
| hf-020 | 99.13ms | 0.188s | 21 | 18.53ms | — |
| hf-021 | 65.50ms | 0.293s | 48 | 75.36ms | — |
| hf-022 | 99.26ms | 0.215s | 40 | 17.06ms | — |
| hf-023 | 81.73ms | 15.073s | 5120 | 77.60ms | — |
| hf-024 | 96.60ms | 0.292s | 42 | 77.55ms | — |
| hf-025 | 99.16ms | 0.295s | 42 | 77.05ms | — |
| hf-026 | 101.34ms | 0.219s | 42 | 17.45ms | — |
| hf-027 | 104.86ms | 0.208s | 24 | 17.76ms | — |
| hf-028 | 92.57ms | 0.294s | 43 | 75.99ms | — |
| hf-029 | 93.92ms | 0.295s | 48 | 75.39ms | — |
| hf-030 | 94.88ms | 0.329s | 54 | 76.29ms | — |
| hf-031 | 96.28ms | 0.199s | 21 | 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