Round score
0.0549
weighted tier speedup after failure cap and deduction
Eligible requests
28
trusted baseline exclusions removed
Failed eligible requests
6
each request counted once
Raw weighted speedup
+7.63%
before failure cap and deduction
Temperature range
Request concurrency
Tier scheduling
Output policy
Thinking
Context limit
The same eligible inputs and output ceilings apply to every engine. Candidates must emit at least 90% of baseline tokens per request; natural output lengths can affect tier completion time. Slots refill until the group drains and stay occupied through protocol completion. Baseline exclusions and final drain can reduce actual concurrency below the configured cap.
Raw weighted speedup
Eligible speedup
Request failures cap speed credit at zero: min(0.076279, 0) = 0.076279. Negative speedups remain negative.
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.
28 prompts
| Prompt | Diagnostic speedup | Baseline | Candidate | Aligned output | Diagnostic / failure |
|---|---|---|---|---|---|
| hf-026 | — | — | — | 2340 | Per-token timing unavailable (not a request failure) |
| hf-001 | — | — | — | 2820 | Per-token timing unavailable (not a request failure) |
| hf-022 | — | — | — |
28 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-001 | 696.41ms | 79.410s | 4709 | 39.00ms | 2316 gaps for 4709 tokens |
| hf-002 | 620.38ms | 59.158s | 4237 | 100.41ms | 1670 gaps for 4237 tokens |
| hf-003 | 697.06ms |
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 | 28 | 28 | 20.51 |
| 2 | 0.000s | C32 | 28 | 28 | 23.84 |
| 3 | 0.000s | C32 | 28 | 28 | 21.42 |
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 |
|---|
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 |
|---|---|---|---|---|---|---|
| 2k | 6 | 25% | 103.068s | 81.523s | +20.90% | +5.23% |
| 4k | 7 | 25% | 104.854s | 95.971s | +8.47% | +2.12% |
| 8k | 7 | 25% | 101.621s | 87.791s | +13.61% | +3.40% |
| 16k | 8 | 25% | 99.499s | 111.909s | -12.47% | -3.12% |
| 2132 |
| Per-token timing unavailable (not a request failure) |
| hf-002 | — | — | — | 3187 | Per-token timing unavailable (not a request failure) |
| hf-008 | — | — | — | 5120 | Per-token timing unavailable (not a request failure) |
| hf-031 | — | — | — | 2654 | Per-token timing unavailable (not a request failure) |
| hf-024 | — | — | — | 3845 | Per-token timing unavailable (not a request failure) |
| hf-009 | — | — | — | 3986 | Per-token timing unavailable (not a request failure) |
| hf-011 | — | — | — | 3482 | Per-token timing unavailable (not a request failure) |
| hf-010 | — | — | — | 2745 | Per-token timing unavailable (not a request failure) |
| hf-005 | — | — | — | 3831 | candidate output below tolerance |
| hf-018 | — | — | — | 3727 | candidate output below tolerance |
| hf-006 | — | — | — | 4654 | Per-token timing unavailable (not a request failure) |
| hf-016 | — | — | — | 4197 | candidate output below tolerance |
| hf-029 | — | — | — | 4661 | Per-token timing unavailable (not a request failure) |
| hf-014 | — | — | — | 3427 | candidate output below tolerance |
| hf-020 | — | — | — | 5120 | Per-token timing unavailable (not a request failure) |
| hf-027 | — | — | — | 3003 | candidate output below tolerance |
| hf-023 | — | — | — | 4400 | Per-token timing unavailable (not a request failure) |
| hf-003 | — | — | — | 5120 | Per-token timing unavailable (not a request failure) |
| hf-019 | — | — | — | 5120 | Per-token timing unavailable (not a request failure) |
| hf-015 | — | — | — | 5120 | Per-token timing unavailable (not a request failure) |
| hf-012 | — | — | — | 5120 | Per-token timing unavailable (not a request failure) |
| hf-025 | — | — | — | 4162 | Per-token timing unavailable (not a request failure) |
| hf-021 | — | — | — | 5120 | Per-token timing unavailable (not a request failure) |
| hf-030 | — | — | — | 5120 | Per-token timing unavailable (not a request failure) |
| hf-013 | — | — | — | 4491 | Per-token timing unavailable (not a request failure) |
| hf-007 | — | — | — | 3589 | candidate output below tolerance |
| 70.951s |
| 5120 |
| 37.23ms |
| 2037 gaps for 5120 tokens |
| hf-005 | 692.21ms | 57.623s | 3831 | 37.78ms | 1633 gaps for 3831 tokens |
| hf-006 | 691.83ms | 78.886s | 5120 | 37.61ms | 2302 gaps for 5120 tokens |
| hf-007 | 695.76ms | 77.856s | 3589 | 39.17ms | 2242 gaps for 3589 tokens |
| hf-008 | 696.20ms | 80.476s | 5120 | 38.35ms | 2378 gaps for 5120 tokens |
| hf-009 | 686.13ms | 72.701s | 4117 | 38.81ms | 2137 gaps for 4117 tokens |
| hf-010 | 683.85ms | 81.343s | 5120 | 39.12ms | 2697 gaps for 5120 tokens |
| hf-011 | 684.84ms | 71.126s | 5120 | 38.91ms | 2066 gaps for 5120 tokens |
| hf-012 | 698.34ms | 78.822s | 5120 | 38.94ms | 2287 gaps for 5120 tokens |
| hf-013 | 677.95ms | 77.026s | 5120 | 39.09ms | 2359 gaps for 5120 tokens |
| hf-014 | 688.57ms | 61.637s | 3427 | 37.53ms | 1751 gaps for 3427 tokens |
| hf-015 | 692.54ms | 80.379s | 5120 | 38.04ms | 2372 gaps for 5120 tokens |
| hf-016 | 679.20ms | 70.321s | 4197 | 39.00ms | 2031 gaps for 4197 tokens |
| hf-018 | 683.59ms | 56.910s | 3727 | 39.36ms | 1615 gaps for 3727 tokens |
| hf-019 | 691.41ms | 78.966s | 5120 | 38.52ms | 2294 gaps for 5120 tokens |
| hf-020 | 677.51ms | 77.131s | 5120 | 39.26ms | 2366 gaps for 5120 tokens |
| hf-021 | 692.03ms | 77.798s | 5120 | 38.72ms | 2240 gaps for 5120 tokens |
| hf-022 | 687.67ms | 61.300s | 4371 | 38.14ms | 1735 gaps for 4371 tokens |
| hf-023 | 683.39ms | 75.334s | 5120 | 38.99ms | 2171 gaps for 5120 tokens |
| hf-024 | 682.07ms | 77.633s | 4540 | 38.83ms | 2243 gaps for 4540 tokens |
| hf-025 | 683.70ms | 70.936s | 4430 | 38.81ms | 2037 gaps for 4430 tokens |
| hf-026 | 686.58ms | 40.965s | 2562 | 38.02ms | 1140 gaps for 2562 tokens |
| hf-027 | 679.60ms | 51.480s | 3003 | 38.62ms | 1450 gaps for 3003 tokens |
| hf-029 | 672.11ms | 73.951s | 5120 | 39.03ms | 2196 gaps for 5120 tokens |
| hf-030 | 680.09ms | 78.211s | 5120 | 39.35ms | 2270 gaps for 5120 tokens |
| hf-031 | 681.59ms | 77.744s | 5120 | 38.73ms | 2248 gaps for 5120 tokens |
| Baseline char-16 |
|---|
| Drop |
|---|
| Limit |
|---|
| Result |
|---|
| hf-001 | 0.9822 | 0.9203 | -0.0620 | 0.1000 | Passed |
| hf-002 | 0.8422 | 0.9763 | 0.1341 | 0.1000 | Failed distinct 16-gram ratio 0.842 is more than 0.10 below baseline 0.976 over 21412 chars |
| hf-003 | 0.9579 | 0.8336 | -0.1243 | 0.1000 | Passed |
| hf-005 | 0.9566 | 0.9704 | 0.0138 | 0.1000 | Passed |
| hf-006 | 0.9654 | 0.9593 | -0.0061 | 0.1000 | Passed |
| hf-007 | 0.9908 | 0.7025 | -0.2883 | 0.1000 | Passed |
| hf-008 | 0.9664 | 0.7725 | -0.1939 | 0.1000 | Passed |
| hf-009 | 0.9871 | 0.9725 | -0.0146 | 0.1000 | Passed |
| hf-010 | 0.9867 | 0.9876 | 0.0009 | 0.1000 | Passed |
| hf-011 | 0.9569 | 0.9432 | -0.0136 | 0.1000 | Passed |
| hf-012 | 0.9568 | 0.9591 | 0.0023 | 0.1000 | Passed |
| hf-013 | 0.9706 | 0.9490 | -0.0216 | 0.1000 | Passed |
| hf-014 | 0.9892 | 0.9603 | -0.0289 | 0.1000 | Passed |
| hf-015 | 0.9739 | 0.9432 | -0.0307 | 0.1000 | Passed |
| hf-016 | 0.9888 | 0.9732 | -0.0156 | 0.1000 | Passed |
| hf-018 | 0.9553 | 0.5820 | -0.3733 | 0.1000 | Passed |
| hf-019 | 0.9491 | 0.9726 | 0.0235 | 0.1000 | Passed |
| hf-020 | 0.9746 | 0.9137 | -0.0609 | 0.1000 | Passed |
| hf-021 | 0.9038 | 0.9389 | 0.0351 | 0.1000 | Passed |
| hf-022 | 0.9026 | 0.9048 | 0.0022 | 0.1000 | Passed |
| hf-023 | 0.9690 | 0.8942 | -0.0749 | 0.1000 | Passed |
| hf-024 | 0.9723 | 0.9312 | -0.0411 | 0.1000 | Passed |
| hf-025 | 0.9582 | 0.9246 | -0.0336 | 0.1000 | Passed |
| hf-026 | 0.9655 | 0.9627 | -0.0028 | 0.1000 | Passed |
| hf-027 | 0.9732 | 0.8809 | -0.0922 | 0.1000 | Passed |
| hf-029 | 0.9716 | 0.9088 | -0.0628 | 0.1000 | Passed |
| hf-030 | 0.9700 | 0.9677 | -0.0023 | 0.1000 | Passed |
| hf-031 | 0.9710 | 0.8850 | -0.0860 | 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-018 | 1 | 0.737151 | 1 | 0 |
| hf-026 | 1 | 0.258588 | 1 | 0 |
| hf-013 | 1 | 0.234207 | 1 | 0 |
| hf-027 | 1 | 0.911383 | 1 | 0 |
| hf-005 | 1 | 0.663059 | 1 | 0 |
| hf-002 | 1 | 0.711992 | 1 | 0 |
| hf-029 | 1 | 0.752413 | 1 | 0 |
| hf-022 | 1 | 0.407771 | 1 | 0 |
| hf-003 | 1 | 0.506793 | 1 | 0 |
| hf-025 | 1 | 0.119657 | 1 | 0 |
| hf-020 | 1 | 0.854241 | 1 | 0 |
| hf-021 | 1 | 0.295024 | 1 | 0 |
| hf-007 | 1 | 0.714609 | 1 | 0 |
| hf-012 | 1 | 0.444494 | 1 | 0 |
| hf-019 | 1 | 0.450884 | 1 | 0 |
| hf-011 | 1 | 0.8957 | 1 | 0 |
| hf-023 | 1 | 0.502734 | 1 | 0 |
| hf-001 | 1 | 0.732727 | 1 | 0 |
| hf-014 | 1 | 0.690995 | 1 | 0 |
| hf-015 | 1 | 0.468658 | 1 | 0 |
| hf-008 | 1 | 0.391391 | 1 | 0 |
| hf-030 | 1 | 0.282037 | 1 | 0 |
| hf-006 | 1 | 0.852864 | 1 | 0 |
| hf-009 | 1 | 0.970461 | 1 | 0 |
| hf-016 | 1 | 0.996831 | 1 | 0 |
| hf-031 | 1 | 0.776567 | 1 | 0 |
| hf-024 | 1 | 0.995315 | 1 | 0 |
| hf-010 | 1 | 0.938026 | 1 | 0 |
| hf-026 | 2 | 0.258588 | 1 | 0 |
| hf-016 | 2 | 0.996831 | 1 | 0 |
| hf-010 | 2 | 0.938026 | 1 | 0 |
| hf-027 | 2 | 0.911383 | 1 | 0 |
| hf-005 | 2 | 0.663059 | 1 | 0 |
| hf-014 | 2 | 0.690995 | 1 | 0 |
| hf-009 | 2 | 0.970461 | 1 | 0 |
| hf-001 | 2 | 0.732727 | 1 | 0 |
| hf-007 | 2 | 0.714609 | 1 | 0 |
| hf-011 | 2 | 0.8957 | 1 | 0 |
| hf-023 | 2 | 0.502734 | 1 | 0 |
| hf-029 | 2 | 0.752413 | 1 | 0 |
| hf-024 | 2 | 0.995315 | 1 | 0 |
| hf-031 | 2 | 0.776567 | 1 | 0 |
| hf-030 | 2 | 0.282037 | 1 | 0 |
| hf-006 | 2 | 0.852864 | 1 | 0 |
| hf-012 | 2 | 0.444494 | 1 | 0 |
| hf-013 | 2 | 0.234207 | 1 | 0 |
| hf-002 | 2 | 0.711992 | 1 | 0 |
| hf-019 | 2 | 0.450884 | 1 | 0 |
| hf-003 | 2 | 0.506793 | 1 | 0 |
| hf-018 | 2 | 0.737151 | 1 | 0 |
| hf-015 | 2 | 0.468658 | 1 | 0 |
| hf-025 | 2 | 0.119657 | 1 | 0 |
| hf-008 | 2 | 0.391391 | 1 | 0 |
| hf-020 | 2 | 0.854241 | 1 | 0 |
| hf-021 | 2 | 0.295024 | 1 | 0 |
| hf-022 | 2 | 0.407771 | 1 | 0 |
| hf-002 | 3 | 0.711992 | 1 | 0 |
| hf-022 | 3 | 0.407771 | 1 | 0 |
| hf-031 | 3 | 0.776567 | 1 | 0 |
| hf-024 | 3 | 0.995315 | 1 | 0 |
| hf-014 | 3 | 0.690995 | 1 | 0 |
| hf-018 | 3 | 0.737151 | 1 | 0 |
| hf-026 | 3 | 0.258588 | 1 | 0 |
| hf-023 | 3 | 0.502734 | 1 | 0 |
| hf-005 | 3 | 0.663059 | 1 | 0 |
| hf-025 | 3 | 0.119657 | 1 | 0 |
| hf-003 | 3 | 0.506793 | 1 | 0 |
| hf-016 | 3 | 0.996831 | 1 | 0 |
| hf-011 | 3 | 0.8957 | 1 | 0 |
| hf-009 | 3 | 0.970461 | 1 | 0 |
| hf-029 | 3 | 0.752413 | 1 | 0 |
| hf-030 | 3 | 0.282037 | 1 | 0 |
| hf-027 | 3 | 0.911383 | 1 | 0 |
| hf-012 | 3 | 0.444494 | 1 | 0 |
| hf-008 | 3 | 0.391391 | 1 | 0 |
| hf-006 | 3 | 0.852864 | 1 | 0 |
| hf-019 | 3 | 0.450884 | 1 | 0 |
| hf-013 | 3 | 0.234207 | 1 | 0 |
| hf-021 | 3 | 0.295024 | 1 | 0 |
| hf-020 | 3 | 0.854241 | 1 | 0 |
| hf-015 | 3 | 0.468658 | 1 | 0 |
| hf-001 | 3 | 0.732727 | 1 | 0 |
| hf-010 | 3 | 0.938026 | 1 | 0 |
| hf-007 | 3 | 0.714609 | 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