Round score
—
degenerate output (hf-018: distinct 16-gram ratio 0.061 below baseline 1.000 over 19188 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-018: distinct 16-gram ratio 0.061 below baseline 1.000 over 19188 chars)
32 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-000 | 208.55ms | 1.888s | 41 | 214.13ms | — |
| hf-001 | 445.35ms | 2.303s | 55 | 212.34ms | — |
| hf-002 | 449.27ms | 2.105s |
reason
verdict
evidence
min logprob
num prompts
mean logprob
coverage ratio
quantile logprob
num positions scored
| 43 |
| 211.74ms |
| — |
| hf-003 | 452.69ms | 2.306s | 57 | 212.73ms | — |
| hf-004 | 459.32ms | 1.706s | 43 | 214.05ms | — |
| hf-005 | 467.75ms | 1.907s | 41 | 211.60ms | — |
| hf-006 | 479.89ms | 2.156s | 43 | 233.77ms | — |
| hf-007 | 440.03ms | 2.404s | 49 | 204.50ms | — |
| hf-008 | 490.72ms | 1.522s | 29 | 214.69ms | — |
| hf-009 | 497.57ms | 2.311s | 53 | 229.90ms | — |
| hf-010 | 609.45ms | 1.828s | 45 | 210.12ms | — |
| hf-011 | 618.81ms | 1.834s | 42 | 212.22ms | — |
| hf-012 | 437.36ms | 2.230s | 54 | 202.78ms | — |
| hf-013 | 632.93ms | 2.038s | 50 | 211.84ms | — |
| hf-014 | 638.48ms | 1.839s | 29 | 213.73ms | — |
| hf-015 | 654.50ms | 1.841s | 43 | 207.26ms | — |
| hf-016 | 455.28ms | 1.645s | 45 | 208.40ms | — |
| hf-017 | 395.36ms | 1.441s | 46 | 208.40ms | — |
| hf-018 | 231.97ms | 21.412s | 5120 | 210.03ms | — |
| hf-019 | 442.42ms | 1.420s | 40 | 204.50ms | — |
| hf-020 | 436.11ms | 2.072s | 62 | 208.99ms | — |
| hf-021 | 439.26ms | 1.663s | 52 | 207.85ms | — |
| hf-022 | 440.48ms | 1.670s | 41 | 208.25ms | — |
| hf-023 | 442.37ms | 1.264s | 41 | 208.56ms | — |
| hf-024 | 429.53ms | 1.060s | 25 | 208.57ms | — |
| hf-025 | 185.78ms | 20.541s | 5120 | 205.87ms | — |
| hf-026 | 441.98ms | 1.374s | 43 | 205.33ms | — |
| hf-027 | 460.23ms | 1.395s | 77 | 206.14ms | — |
| hf-028 | 464.05ms | 1.139s | 70 | 208.50ms | — |
| hf-029 | 461.81ms | 0.851s | 51 | 206.54ms | — |
| hf-030 | 445.27ms | 0.916s | 89 | 38.53ms | — |
| hf-031 | 304.21ms | 0.541s | 47 | 32.60ms | — |
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