Round score
—
degenerate output (repeated-span failures exceed allowance of 4 prompts (hf-018: rep 1: longest repeated span ratio 0.804 at or above harness ceiling over 22775 chars))
Eligible requests
—
trusted baseline exclusions removed
Failed eligible requests
—
each request counted once
Raw weighted speedup
—
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.
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.
No prompt scores
degenerate output (repeated-span failures exceed allowance of 4 prompts (hf-018: rep 1: longest repeated span ratio 0.804 at or above harness ceiling over 22775 chars))
28 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-001 | 687.16ms | 72.275s | 4366 | 42.79ms | 1826 gaps for 4366 tokens |
| hf-002 | 613.56ms | 85.493s | 5120 | 113.50ms | 2172 gaps for 5120 tokens |
| hf-003 | 676.92ms |
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 | 18.37 |
| 2 | 0.000s | C32 | 28 | 28 | 19.04 |
| 3 | 0.000s | C32 | 28 | 28 | 17.86 |
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 |
|---|
| 84.771s |
| 4875 |
| 47.58ms |
| 2196 gaps for 4875 tokens |
| hf-005 | 687.31ms | 44.775s | 2571 | 43.04ms | 1094 gaps for 2571 tokens |
| hf-006 | 685.39ms | 49.454s | 3141 | 44.39ms | 1216 gaps for 3141 tokens |
| hf-007 | 688.67ms | 50.253s | 2177 | 43.33ms | 1215 gaps for 2177 tokens |
| hf-008 | 681.82ms | 96.113s | 5120 | 42.79ms | 2569 gaps for 5120 tokens |
| hf-009 | 676.56ms | 52.303s | 3838 | 50.10ms | 1280 gaps for 3838 tokens |
| hf-010 | 684.92ms | 73.078s | 5120 | 45.32ms | 1820 gaps for 5120 tokens |
| hf-011 | 676.12ms | 47.139s | 2994 | 47.89ms | 1146 gaps for 2994 tokens |
| hf-012 | 673.38ms | 94.466s | 5117 | 50.70ms | 2532 gaps for 5117 tokens |
| hf-013 | 677.22ms | 89.813s | 3967 | 43.70ms | 2349 gaps for 3967 tokens |
| hf-014 | 681.28ms | 70.819s | 4259 | 42.80ms | 1786 gaps for 4259 tokens |
| hf-015 | 671.38ms | 60.533s | 3220 | 50.06ms | 1505 gaps for 3220 tokens |
| hf-016 | 669.02ms | 44.435s | 2908 | 47.69ms | 1077 gaps for 2908 tokens |
| hf-018 | 669.32ms | 58.016s | 3433 | 49.84ms | 1436 gaps for 3433 tokens |
| hf-019 | 678.46ms | 91.962s | 5120 | 43.42ms | 2423 gaps for 5120 tokens |
| hf-020 | 666.26ms | 76.952s | 5120 | 51.10ms | 1963 gaps for 5120 tokens |
| hf-021 | 668.23ms | 101.005s | 5120 | 49.54ms | 2807 gaps for 5120 tokens |
| hf-022 | 680.76ms | 64.521s | 3150 | 45.71ms | 1587 gaps for 3150 tokens |
| hf-023 | 682.83ms | 88.994s | 4727 | 46.04ms | 2278 gaps for 4727 tokens |
| hf-024 | 666.74ms | 43.179s | 2965 | 50.60ms | 1046 gaps for 2965 tokens |
| hf-025 | 673.96ms | 111.152s | 5120 | 43.32ms | 3213 gaps for 5120 tokens |
| hf-026 | 667.21ms | 84.393s | 3985 | 50.33ms | 2185 gaps for 3985 tokens |
| hf-027 | 679.93ms | 76.107s | 5120 | 46.02ms | 1903 gaps for 5120 tokens |
| hf-029 | 673.12ms | 77.828s | 5120 | 43.42ms | 1982 gaps for 5120 tokens |
| hf-030 | 675.21ms | 101.632s | 5120 | 43.63ms | 2789 gaps for 5120 tokens |
| hf-031 | 681.63ms | 42.836s | 2713 | 43.02ms | 1030 gaps for 2713 tokens |
| Baseline char-16 |
|---|
| Drop |
|---|
| Limit |
|---|
| Result |
|---|
| hf-001 | 0.9283 | 0.9203 | -0.0080 | 0.1000 | Failed rep 1: longest repeated span ratio 0.725 at or above harness ceiling over 22602 chars |
| hf-002 | 0.8468 | 0.9763 | 0.1295 | 0.1000 | Failed distinct 16-gram ratio 0.847 is more than 0.10 below baseline 0.976 over 25013 chars |
| hf-003 | 0.8246 | 0.8336 | 0.0090 | 0.1000 | Passed |
| hf-005 | 0.9053 | 0.9704 | 0.0651 | 0.1000 | Passed |
| hf-006 | 0.9238 | 0.9593 | 0.0355 | 0.1000 | Passed |
| hf-007 | 0.9324 | 0.7025 | -0.2299 | 0.1000 | Failed rep 3: longest repeated span ratio 0.459 at or above harness ceiling over 25108 chars |
| hf-008 | 0.6874 | 0.7725 | 0.0851 | 0.1000 | Passed |
| hf-009 | 0.6995 | 0.9725 | 0.2730 | 0.1000 | Failed rep 3: longest repeated span ratio 0.350 at or above harness ceiling over 24968 chars |
| hf-010 | 0.6067 | 0.9876 | 0.3809 | 0.1000 | Failed longest repeated span ratio 0.324 at or above harness ceiling over 21688 chars |
| hf-011 | 0.9502 | 0.9432 | -0.0070 | 0.1000 | Passed |
| hf-012 | 0.9645 | 0.9591 | -0.0054 | 0.1000 | Passed |
| hf-013 | 0.9661 | 0.9490 | -0.0171 | 0.1000 | Passed |
| hf-014 | 0.8840 | 0.9603 | 0.0764 | 0.1000 | Passed |
| hf-015 | 0.9242 | 0.9432 | 0.0190 | 0.1000 | Passed |
| hf-016 | 0.9694 | 0.9732 | 0.0038 | 0.1000 | Passed |
| hf-018 | 0.8601 | 0.5820 | -0.2781 | 0.1000 | Failed rep 1: longest repeated span ratio 0.804 at or above harness ceiling over 22775 chars |
| hf-019 | 0.9468 | 0.9726 | 0.0258 | 0.1000 | Passed |
| hf-020 | 0.9233 | 0.9137 | -0.0096 | 0.1000 | Passed |
| hf-021 | 0.9389 | 0.9389 | -0.0000 | 0.1000 | Passed |
| hf-022 | 0.9454 | 0.9048 | -0.0406 | 0.1000 | Passed |
| hf-023 | 0.8118 | 0.8942 | 0.0824 | 0.1000 | Passed |
| hf-024 | 0.9005 | 0.9312 | 0.0306 | 0.1000 | Failed rep 1: longest repeated span ratio 0.677 at or above harness ceiling over 21008 chars |
| hf-025 | 0.9201 | 0.9246 | 0.0046 | 0.1000 | Passed |
| hf-026 | 0.9709 | 0.9627 | -0.0082 | 0.1000 | Passed |
| hf-027 | 0.6215 | 0.8809 | 0.2595 | 0.1000 | Failed rep 3: distinct 16-gram ratio 0.148 below harness floor over 23866 chars |
| hf-029 | 0.7812 | 0.9088 | 0.1276 | 0.1000 | Failed rep 1: longest repeated span ratio 0.499 at or above harness ceiling over 23768 chars |
| hf-030 | 0.9508 | 0.9677 | 0.0169 | 0.1000 | Passed |
| hf-031 | 0.8110 | 0.8850 | 0.0740 | 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-026 | 1 | 0.258588 | 1 | 0 |
| hf-031 | 1 | 0.776567 | 1 | 0 |
| hf-006 | 1 | 0.852864 | 1 | 0 |
| hf-015 | 1 | 0.468658 | 1 | 0 |
| hf-005 | 1 | 0.663059 | 1 | 0 |
| hf-007 | 1 | 0.714609 | 1 | 0 |
| hf-009 | 1 | 0.970461 | 1 | 0 |
| hf-016 | 1 | 0.996831 | 1 | 0 |
| hf-014 | 1 | 0.690995 | 1 | 0 |
| hf-024 | 1 | 0.995315 | 1 | 0 |
| hf-022 | 1 | 0.407771 | 1 | 0 |
| hf-029 | 1 | 0.752413 | 1 | 0 |
| hf-010 | 1 | 0.938026 | 1 | 0 |
| hf-027 | 1 | 0.911383 | 1 | 0 |
| hf-020 | 1 | 0.854241 | 1 | 0 |
| hf-011 | 1 | 0.8957 | 1 | 0 |
| hf-002 | 1 | 0.711992 | 1 | 0 |
| hf-003 | 1 | 0.506793 | 1 | 0 |
| hf-023 | 1 | 0.502734 | 1 | 0 |
| hf-018 | 1 | 0.737151 | 1 | 0 |
| hf-001 | 1 | 0.732727 | 1 | 0 |
| hf-019 | 1 | 0.450884 | 1 | 0 |
| hf-012 | 1 | 0.444494 | 1 | 0 |
| hf-008 | 1 | 0.391391 | 1 | 0 |
| hf-021 | 1 | 0.295024 | 1 | 0 |
| hf-030 | 1 | 0.282037 | 1 | 0 |
| hf-013 | 1 | 0.234207 | 1 | 0 |
| hf-025 | 1 | 0.119657 | 1 | 0 |
| hf-031 | 2 | 0.776567 | 1 | 0 |
| hf-005 | 2 | 0.663059 | 1 | 0 |
| hf-024 | 2 | 0.995315 | 1 | 0 |
| hf-016 | 2 | 0.996831 | 1 | 0 |
| hf-011 | 2 | 0.8957 | 1 | 0 |
| hf-007 | 2 | 0.714609 | 1 | 0 |
| hf-002 | 2 | 0.711992 | 1 | 0 |
| hf-013 | 2 | 0.234207 | 1 | 0 |
| hf-001 | 2 | 0.732727 | 1 | 0 |
| hf-009 | 2 | 0.970461 | 1 | 0 |
| hf-027 | 2 | 0.911383 | 1 | 0 |
| hf-018 | 2 | 0.737151 | 1 | 0 |
| hf-022 | 2 | 0.407771 | 1 | 0 |
| hf-015 | 2 | 0.468658 | 1 | 0 |
| hf-006 | 2 | 0.852864 | 1 | 0 |
| hf-020 | 2 | 0.854241 | 1 | 0 |
| hf-014 | 2 | 0.690995 | 1 | 0 |
| hf-010 | 2 | 0.938026 | 1 | 0 |
| hf-026 | 2 | 0.258588 | 1 | 0 |
| hf-003 | 2 | 0.506793 | 1 | 0 |
| hf-025 | 2 | 0.119657 | 1 | 0 |
| hf-019 | 2 | 0.450884 | 1 | 0 |
| hf-029 | 2 | 0.752413 | 1 | 0 |
| hf-023 | 2 | 0.502734 | 1 | 0 |
| hf-012 | 2 | 0.444494 | 1 | 0 |
| hf-008 | 2 | 0.391391 | 1 | 0 |
| hf-030 | 2 | 0.282037 | 1 | 0 |
| hf-021 | 2 | 0.295024 | 1 | 0 |
| hf-010 | 3 | 0.938026 | 1 | 0 |
| hf-016 | 3 | 0.996831 | 1 | 0 |
| hf-011 | 3 | 0.8957 | 1 | 0 |
| hf-024 | 3 | 0.995315 | 1 | 0 |
| hf-023 | 3 | 0.502734 | 1 | 0 |
| hf-005 | 3 | 0.663059 | 1 | 0 |
| hf-006 | 3 | 0.852864 | 1 | 0 |
| hf-031 | 3 | 0.776567 | 1 | 0 |
| hf-018 | 3 | 0.737151 | 1 | 0 |
| hf-009 | 3 | 0.970461 | 1 | 0 |
| hf-015 | 3 | 0.468658 | 1 | 0 |
| hf-014 | 3 | 0.690995 | 1 | 0 |
| hf-020 | 3 | 0.854241 | 1 | 0 |
| hf-001 | 3 | 0.732727 | 1 | 0 |
| hf-021 | 3 | 0.295024 | 1 | 0 |
| hf-029 | 3 | 0.752413 | 1 | 0 |
| hf-027 | 3 | 0.911383 | 1 | 0 |
| hf-003 | 3 | 0.506793 | 1 | 0 |
| hf-007 | 3 | 0.714609 | 1 | 0 |
| hf-012 | 3 | 0.444494 | 1 | 0 |
| hf-002 | 3 | 0.711992 | 1 | 0 |
| hf-013 | 3 | 0.234207 | 1 | 0 |
| hf-019 | 3 | 0.450884 | 1 | 0 |
| hf-008 | 3 | 0.391391 | 1 | 0 |
| hf-022 | 3 | 0.407771 | 1 | 0 |
| hf-026 | 3 | 0.258588 | 1 | 0 |
| hf-030 | 3 | 0.282037 | 1 | 0 |
| hf-025 | 3 | 0.119657 | 1 | 0 |
reason
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