Round score
0.3303
weighted tier speedup after failure cap and deduction
Eligible requests
29
trusted baseline exclusions removed
Failed eligible requests
3
each request counted once
Raw weighted speedup
+34.07%
before failure cap and deduction
Raw weighted speedup
Eligible speedup
Request failures cap speed credit at zero: min(0.340658, 0) = 0.340658. Negative speedups remain negative.
Failed requests
Deduction
Final score
Each duration is the median across repetitions, from the group start until the tier's last request finishes. This includes client queueing. Weighted speedup = sum of weight × (1 − candidate / baseline).
| Input tier | Eligible requests | Weight | Baseline | Candidate | Speedup | Contribution |
|---|---|---|---|---|---|---|
The round score uses weighted completion times for all eligible work in each tier. Per-request speedups below are diagnostics, not score contributions. Only trusted baseline exclusions are removed; candidate failures remain in the eligible count and incur the configured failure penalty.
29 prompts
| Prompt | Diagnostic speedup | Baseline | Candidate | Aligned output | Diagnostic / failure |
|---|---|---|---|---|---|
| hf-001 | — | — | — | 5120 | Per-token timing unavailable (not a request failure) |
| hf-030 | — | — | — | 3262 | Per-token timing unavailable (not a request failure) |
| hf-022 | — | — | — |
29 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-000 | 962.17ms | 48.828s | 3137 | 1.036s | 1145 gaps for 3137 tokens |
| hf-001 | 2.090s | 68.426s | 5120 | 45.83ms | 1617 gaps for 5120 tokens |
| hf-002 | 1.837s | 70.992s |
Occupied client slots include protocol completion and final drain. Mean occupancy is weighted by elapsed time; it can be below the requested cap.
| Repetition | Group start | Requested | Effective cap | Peak | Mean |
|---|---|---|---|---|---|
| 1 | 0.000s | C32 | 29 | 29 | 24.73 |
| 2 | 0.000s | C32 | 29 | 29 | 26.58 |
| 3 | 0.000s | C32 | 29 | 29 | 23.84 |
Each latency-median response is compared with the lowest valid opening-baseline ratio for the same prompt. Drops above the recorded limit fail; absolute checks also apply. These checks detect repetition, not overall writing quality.
| Prompt | Candidate char-16 |
|---|
| 16k |
|---|
| 8 |
| 25% |
| 121.650s |
| 78.489s |
| +35.48% |
| +8.87% |
| 32k | 8 | 25% | 116.561s | 84.222s | +27.74% | +6.94% |
|---|
| 64k | 7 | 25% | 121.318s | 75.384s | +37.86% | +9.47% |
|---|
| 128k | 6 | 25% | 120.339s | 78.008s | +35.18% | +8.79% |
|---|
| 4240 |
| Per-token timing unavailable (not a request failure) |
| hf-006 | — | — | — | 3326 | Per-token timing unavailable (not a request failure) |
| hf-027 | — | — | — | 3420 | Per-token timing unavailable (not a request failure) |
| hf-017 | — | — | — | 5070 | Per-token timing unavailable (not a request failure) |
| hf-016 | — | — | — | 5120 | Per-token timing unavailable (not a request failure) |
| hf-013 | — | — | — | 5120 | Per-token timing unavailable (not a request failure) |
| hf-000 | — | — | — | 3121 | Per-token timing unavailable (not a request failure) |
| hf-021 | — | — | — | 5120 | Per-token timing unavailable (not a request failure) |
| hf-020 | — | — | — | 5120 | Per-token timing unavailable (not a request failure) |
| hf-003 | — | — | — | 5120 | Per-token timing unavailable (not a request failure) |
| hf-005 | — | — | — | 3472 | Per-token timing unavailable (not a request failure) |
| hf-011 | — | — | — | 4306 | Per-token timing unavailable (not a request failure) |
| hf-029 | — | — | — | 5120 | Per-token timing unavailable (not a request failure) |
| hf-009 | — | — | — | 5120 | Per-token timing unavailable (not a request failure) |
| hf-018 | — | — | — | 5120 | Per-token timing unavailable (not a request failure) |
| hf-019 | — | — | — | 5120 | Per-token timing unavailable (not a request failure) |
| hf-002 | — | — | — | 5120 | Per-token timing unavailable (not a request failure) |
| hf-007 | — | — | — | 5120 | Per-token timing unavailable (not a request failure) |
| hf-023 | — | — | — | 3725 | candidate output below tolerance |
| hf-028 | — | — | — | 4006 | candidate output below tolerance |
| hf-012 | — | — | — | 5120 | Per-token timing unavailable (not a request failure) |
| hf-026 | — | — | — | 5120 | Per-token timing unavailable (not a request failure) |
| hf-010 | — | — | — | 5120 | Per-token timing unavailable (not a request failure) |
| hf-025 | — | — | — | 5120 | Per-token timing unavailable (not a request failure) |
| hf-031 | — | — | — | 5120 | Per-token timing unavailable (not a request failure) |
| hf-014 | — | — | — | 5120 | Per-token timing unavailable (not a request failure) |
| hf-024 | — | — | — | 3859 | candidate output below tolerance |
| 5120 |
| 46.73ms |
| 1660 gaps for 5120 tokens |
| hf-003 | 1.833s | 71.113s | 5120 | 46.74ms | 1665 gaps for 5120 tokens |
| hf-005 | 2.091s | 71.170s | 4839 | 45.83ms | 1703 gaps for 4839 tokens |
| hf-006 | 1.835s | 69.560s | 4533 | 46.73ms | 1615 gaps for 4533 tokens |
| hf-007 | 1.836s | 69.740s | 5120 | 46.73ms | 1620 gaps for 5120 tokens |
| hf-009 | 1.951s | 70.904s | 5120 | 46.33ms | 1819 gaps for 5120 tokens |
| hf-010 | 2.088s | 67.376s | 5120 | 45.84ms | 1589 gaps for 5120 tokens |
| hf-011 | 1.956s | 68.532s | 5120 | 46.24ms | 1691 gaps for 5120 tokens |
| hf-012 | 1.844s | 71.781s | 5120 | 47.80ms | 1696 gaps for 5120 tokens |
| hf-013 | 1.956s | 70.781s | 5120 | 46.33ms | 1811 gaps for 5120 tokens |
| hf-014 | 2.085s | 65.949s | 5120 | 45.50ms | 1553 gaps for 5120 tokens |
| hf-016 | 2.090s | 70.197s | 5120 | 46.67ms | 1666 gaps for 5120 tokens |
| hf-017 | 1.954s | 69.753s | 5070 | 46.06ms | 1753 gaps for 5070 tokens |
| hf-018 | 1.836s | 70.875s | 5120 | 47.74ms | 1656 gaps for 5120 tokens |
| hf-019 | 1.953s | 65.334s | 5120 | 46.06ms | 1562 gaps for 5120 tokens |
| hf-020 | 1.834s | 72.531s | 5120 | 47.67ms | 1740 gaps for 5120 tokens |
| hf-021 | 1.830s | 71.359s | 5120 | 47.44ms | 1676 gaps for 5120 tokens |
| hf-022 | 2.085s | 71.386s | 4811 | 46.58ms | 1713 gaps for 4811 tokens |
| hf-023 | 1.831s | 61.756s | 3725 | 45.77ms | 1420 gaps for 3725 tokens |
| hf-024 | 2.081s | 56.715s | 3859 | 46.43ms | 1324 gaps for 3859 tokens |
| hf-025 | 1.826s | 68.881s | 5120 | 47.40ms | 1598 gaps for 5120 tokens |
| hf-026 | 2.076s | 70.586s | 5120 | 47.40ms | 1681 gaps for 5120 tokens |
| hf-027 | 1.824s | 70.290s | 3926 | 47.28ms | 1636 gaps for 3926 tokens |
| hf-028 | 2.082s | 68.084s | 4006 | 47.35ms | 1608 gaps for 4006 tokens |
| hf-029 | 1.828s | 71.024s | 5120 | 47.30ms | 1662 gaps for 5120 tokens |
| hf-030 | 2.077s | 52.184s | 3500 | 46.38ms | 1213 gaps for 3500 tokens |
| hf-031 | 2.059s | 73.089s | 5120 | 47.31ms | 1796 gaps for 5120 tokens |
| Baseline char-16 |
|---|
| Drop |
|---|
| Limit |
|---|
| Result |
|---|
| hf-000 | 0.8214 | 0.6532 | -0.1682 | 0.1000 | Passed |
| hf-001 | 0.7293 | 0.7253 | -0.0040 | 0.1000 | Passed |
| hf-002 | 0.7708 | 0.6755 | -0.0953 | 0.1000 | Passed |
| hf-003 | 0.7374 | 0.6417 | -0.0957 | 0.1000 | Passed |
| hf-005 | 0.7707 | 0.8205 | 0.0497 | 0.1000 | Passed |
| hf-006 | 0.8641 | 0.9420 | 0.0779 | 0.1000 | Passed |
| hf-007 | 0.7355 | 0.5829 | -0.1526 | 0.1000 | Passed |
| hf-009 | 0.9135 | 0.7753 | -0.1381 | 0.1000 | Passed |
| hf-010 | 0.6690 | 0.7463 | 0.0773 | 0.1000 | Passed |
| hf-011 | 0.6367 | 0.6971 | 0.0605 | 0.1000 | Passed |
| hf-012 | 0.7985 | 0.7874 | -0.0111 | 0.1000 | Passed |
| hf-013 | 0.8952 | 0.8404 | -0.0548 | 0.1000 | Passed |
| hf-014 | 0.7201 | 0.7632 | 0.0431 | 0.1000 | Passed |
| hf-016 | 0.7752 | 0.8207 | 0.0455 | 0.1000 | Passed |
| hf-017 | 0.7291 | 0.7281 | -0.0011 | 0.1000 | Passed |
| hf-018 | 0.6532 | 0.6505 | -0.0028 | 0.1000 | Passed |
| hf-019 | 0.7095 | 0.7296 | 0.0201 | 0.1000 | Passed |
| hf-020 | 0.8058 | 0.8612 | 0.0555 | 0.1000 | Passed |
| hf-021 | 0.7392 | 0.7980 | 0.0588 | 0.1000 | Passed |
| hf-022 | 0.8771 | 0.8596 | -0.0175 | 0.1000 | Passed |
| hf-023 | 0.8268 | 0.7329 | -0.0939 | 0.1000 | Passed |
| hf-024 | 0.7505 | 0.7422 | -0.0082 | 0.1000 | Passed |
| hf-025 | 0.7589 | 0.7315 | -0.0274 | 0.1000 | Passed |
| hf-026 | 0.7976 | 0.8155 | 0.0180 | 0.1000 | Passed |
| hf-027 | 0.9282 | 0.5957 | -0.3326 | 0.1000 | Passed |
| hf-028 | 0.8901 | 0.7612 | -0.1288 | 0.1000 | Passed |
| hf-029 | 0.7778 | 0.7455 | -0.0322 | 0.1000 | Passed |
| hf-030 | 0.8576 | 0.8648 | 0.0072 | 0.1000 | Passed |
| hf-031 | 0.8315 | 0.8597 | 0.0282 | 0.1000 | Passed |
Actual settings for each measured request. Each prompt keeps its temperature across repetitions and engines. Generation uses seed 0 throughout qualification, warmups and measured repetitions; fixed settings do not guarantee identical output text.
| Prompt | Repetition | Temperature | Top p | Seed |
|---|---|---|---|---|
| hf-023 | 1 | 0.485263 | 1 | 0 |
| hf-000 | 1 | 0.101237 | 1 | 0 |
| hf-030 | 1 | 0.476485 | 1 | 0 |
| hf-024 | 1 | 0.121643 | 1 | 0 |
| hf-019 | 1 | 0.382532 | 1 | 0 |
| hf-014 | 1 | 0.248189 | 1 | 0 |
| hf-010 | 1 | 0.319315 | 1 | 0 |
| hf-012 | 1 | 0.350242 | 1 | 0 |
| hf-028 | 1 | 0.165048 | 1 | 0 |
| hf-001 | 1 | 0.444844 | 1 | 0 |
| hf-017 | 1 | 0.913776 | 1 | 0 |
| hf-009 | 1 | 0.602937 | 1 | 0 |
| hf-016 | 1 | 0.940146 | 1 | 0 |
| hf-026 | 1 | 0.240206 | 1 | 0 |
| hf-011 | 1 | 0.548234 | 1 | 0 |
| hf-002 | 1 | 0.426332 | 1 | 0 |
| hf-005 | 1 | 0.760143 | 1 | 0 |
| hf-022 | 1 | 0.985248 | 1 | 0 |
| hf-003 | 1 | 0.740817 | 1 | 0 |
| hf-021 | 1 | 0.504238 | 1 | 0 |
| hf-025 | 1 | 0.298822 | 1 | 0 |
| hf-031 | 1 | 0.106656 | 1 | 0 |
| hf-013 | 1 | 0.726073 | 1 | 0 |
| hf-029 | 1 | 0.316805 | 1 | 0 |
| hf-018 | 1 | 0.221058 | 1 | 0 |
| hf-020 | 1 | 0.921463 | 1 | 0 |
| hf-027 | 1 | 0.901469 | 1 | 0 |
| hf-007 | 1 | 0.412296 | 1 | 0 |
| hf-006 | 1 | 0.8152 | 1 | 0 |
| hf-000 | 2 | 0.101237 | 1 | 0 |
| hf-013 | 2 | 0.726073 | 1 | 0 |
| hf-023 | 2 | 0.485263 | 1 | 0 |
| hf-030 | 2 | 0.476485 | 1 | 0 |
| hf-014 | 2 | 0.248189 | 1 | 0 |
| hf-011 | 2 | 0.548234 | 1 | 0 |
| hf-010 | 2 | 0.319315 | 1 | 0 |
| hf-025 | 2 | 0.298822 | 1 | 0 |
| hf-006 | 2 | 0.8152 | 1 | 0 |
| hf-007 | 2 | 0.412296 | 1 | 0 |
| hf-017 | 2 | 0.913776 | 1 | 0 |
| hf-027 | 2 | 0.901469 | 1 | 0 |
| hf-024 | 2 | 0.121643 | 1 | 0 |
| hf-018 | 2 | 0.221058 | 1 | 0 |
| hf-002 | 2 | 0.426332 | 1 | 0 |
| hf-029 | 2 | 0.316805 | 1 | 0 |
| hf-003 | 2 | 0.740817 | 1 | 0 |
| hf-001 | 2 | 0.444844 | 1 | 0 |
| hf-021 | 2 | 0.504238 | 1 | 0 |
| hf-019 | 2 | 0.382532 | 1 | 0 |
| hf-026 | 2 | 0.240206 | 1 | 0 |
| hf-012 | 2 | 0.350242 | 1 | 0 |
| hf-009 | 2 | 0.602937 | 1 | 0 |
| hf-005 | 2 | 0.760143 | 1 | 0 |
| hf-020 | 2 | 0.921463 | 1 | 0 |
| hf-016 | 2 | 0.940146 | 1 | 0 |
| hf-028 | 2 | 0.165048 | 1 | 0 |
| hf-031 | 2 | 0.106656 | 1 | 0 |
| hf-022 | 2 | 0.985248 | 1 | 0 |
| hf-003 | 3 | 0.740817 | 1 | 0 |
| hf-006 | 3 | 0.8152 | 1 | 0 |
| hf-030 | 3 | 0.476485 | 1 | 0 |
| hf-000 | 3 | 0.101237 | 1 | 0 |
| hf-024 | 3 | 0.121643 | 1 | 0 |
| hf-007 | 3 | 0.412296 | 1 | 0 |
| hf-025 | 3 | 0.298822 | 1 | 0 |
| hf-001 | 3 | 0.444844 | 1 | 0 |
| hf-010 | 3 | 0.319315 | 1 | 0 |
| hf-018 | 3 | 0.221058 | 1 | 0 |
| hf-027 | 3 | 0.901469 | 1 | 0 |
| hf-005 | 3 | 0.760143 | 1 | 0 |
| hf-019 | 3 | 0.382532 | 1 | 0 |
| hf-028 | 3 | 0.165048 | 1 | 0 |
| hf-002 | 3 | 0.426332 | 1 | 0 |
| hf-014 | 3 | 0.248189 | 1 | 0 |
| hf-026 | 3 | 0.240206 | 1 | 0 |
| hf-029 | 3 | 0.316805 | 1 | 0 |
| hf-011 | 3 | 0.548234 | 1 | 0 |
| hf-022 | 3 | 0.985248 | 1 | 0 |
| hf-016 | 3 | 0.940146 | 1 | 0 |
| hf-020 | 3 | 0.921463 | 1 | 0 |
| hf-017 | 3 | 0.913776 | 1 | 0 |
| hf-021 | 3 | 0.504238 | 1 | 0 |
| hf-013 | 3 | 0.726073 | 1 | 0 |
| hf-031 | 3 | 0.106656 | 1 | 0 |
| hf-009 | 3 | 0.602937 | 1 | 0 |
| hf-012 | 3 | 0.350242 | 1 | 0 |
| hf-023 | 3 | 0.485263 | 1 | 0 |
verdict
evidence
min logprob
num prompts
mean logprob
coverage ratio
quantile logprob
num positions scored
role
evidence
request concurrency
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
tier completion max rel range
Image digest
Patch hash