Round score
—
degenerate output (hf-014: longest repeated span ratio 0.327 at or above harness ceiling over 171 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-014: longest repeated span ratio 0.327 at or above harness ceiling over 171 chars)
32 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-000 | 174.87ms | 0.403s | 44 | 85.92ms | — |
| hf-001 | 176.15ms | 0.486s | 43 | 71.61ms | — |
| hf-002 | 154.83ms | 0.489s |
reason
verdict
evidence
min logprob
num prompts
mean logprob
coverage ratio
quantile logprob
num positions scored
| 52 |
| 84.47ms |
| — |
| hf-003 | 166.06ms | 0.605s | 40 | 103.36ms | — |
| hf-004 | 175.30ms | 0.431s | 28 | 103.59ms | — |
| hf-005 | 204.36ms | 1.087s | 62 | 149.38ms | — |
| hf-006 | 217.45ms | 0.719s | 57 | 149.38ms | — |
| hf-007 | 177.51ms | 0.761s | 65 | 149.20ms | — |
| hf-008 | 243.46ms | 0.613s | 43 | 78.52ms | — |
| hf-009 | 198.08ms | 0.481s | 42 | 73.54ms | — |
| hf-010 | 161.33ms | 0.501s | 48 | 93.51ms | — |
| hf-011 | 187.45ms | 0.560s | 42 | 102.87ms | — |
| hf-012 | 204.03ms | 0.479s | 44 | 69.48ms | — |
| hf-013 | 159.32ms | 0.330s | 44 | 56.07ms | — |
| hf-014 | 75.39ms | 14.210s | 5120 | 106.44ms | — |
| hf-015 | 137.77ms | 0.290s | 41 | 61.54ms | — |
| hf-016 | 162.55ms | 0.416s | 44 | 75.20ms | — |
| hf-017 | 150.64ms | 0.544s | 58 | 76.12ms | — |
| hf-018 | 157.08ms | 0.270s | 18 | 59.20ms | — |
| hf-019 | 165.41ms | 0.557s | 57 | 75.29ms | — |
| hf-020 | 146.80ms | 0.281s | 23 | 61.60ms | — |
| hf-021 | 159.58ms | 0.556s | 62 | 79.19ms | — |
| hf-022 | 166.10ms | 0.541s | 58 | 79.71ms | — |
| hf-023 | 156.81ms | 0.365s | 50 | 58.00ms | — |
| hf-024 | 113.52ms | 13.464s | 5120 | 106.89ms | — |
| hf-025 | 188.85ms | 0.606s | 46 | 82.40ms | — |
| hf-026 | 154.87ms | 0.603s | 54 | 97.67ms | — |
| hf-027 | 177.38ms | 0.601s | 47 | 95.57ms | — |
| hf-028 | 204.10ms | 0.614s | 50 | 106.72ms | — |
| hf-029 | 173.80ms | 0.598s | 45 | 104.75ms | — |
| hf-030 | 214.63ms | 0.446s | 43 | 79.87ms | — |
| hf-031 | 168.68ms | 0.336s | 55 | 31.98ms | — |
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