Round score
—
token logprob at quantile 0.001 is -16.647, below -12.0
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
token logprob at quantile 0.001 is -16.647, below -12.0
32 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-000 | 143.84ms | 0.559s | 41 | 134.68ms | — |
| hf-001 | 180.24ms | 0.835s | 67 | 132.51ms | — |
| hf-002 | 171.84ms | 0.430s |
reason
verdict
evidence
min logprob
num prompts
mean logprob
coverage ratio
quantile logprob
num positions scored
| 28 |
| 130.51ms |
| — |
| hf-003 | 198.06ms | 0.783s | 48 | 132.81ms | — |
| hf-004 | 189.17ms | 0.611s | 45 | 139.38ms | — |
| hf-005 | 195.13ms | 0.627s | 40 | 139.69ms | — |
| hf-006 | 185.24ms | 0.757s | 43 | 137.93ms | — |
| hf-007 | 201.12ms | 0.841s | 70 | 126.70ms | — |
| hf-008 | 180.07ms | 0.588s | 41 | 126.81ms | — |
| hf-009 | 183.18ms | 1.168s | 75 | 130.05ms | — |
| hf-010 | 188.23ms | 0.641s | 48 | 134.81ms | — |
| hf-011 | 204.66ms | 0.756s | 42 | 132.24ms | — |
| hf-012 | 202.98ms | 0.645s | 42 | 135.73ms | — |
| hf-013 | 202.12ms | 0.776s | 50 | 132.81ms | — |
| hf-014 | 194.90ms | 0.585s | 31 | 132.06ms | — |
| hf-015 | 189.52ms | 0.587s | 43 | 133.21ms | — |
| hf-016 | 201.51ms | 0.746s | 45 | 133.16ms | — |
| hf-017 | 188.83ms | 0.601s | 42 | 129.74ms | — |
| hf-018 | 194.01ms | 0.762s | 47 | 129.83ms | — |
| hf-019 | 176.08ms | 0.563s | 42 | 129.73ms | — |
| hf-020 | 181.25ms | 0.790s | 58 | 137.37ms | — |
| hf-021 | 187.28ms | 0.615s | 41 | 137.53ms | — |
| hf-022 | 201.48ms | 0.595s | 41 | 136.53ms | — |
| hf-023 | 208.81ms | 0.601s | 41 | 136.12ms | — |
| hf-024 | 194.02ms | 0.400s | 21 | 128.60ms | — |
| hf-025 | 175.16ms | 0.611s | 42 | 128.88ms | — |
| hf-026 | 176.75ms | 0.622s | 43 | 130.95ms | — |
| hf-027 | 189.39ms | 0.629s | 42 | 130.85ms | — |
| hf-028 | 192.45ms | 0.881s | 75 | 137.64ms | — |
| hf-029 | 172.80ms | 0.630s | 44 | 137.66ms | — |
| hf-030 | 190.65ms | 0.531s | 43 | 137.71ms | — |
| hf-031 | 206.01ms | 0.454s | 47 | 26.04ms | — |
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