Round score
—
degenerate output (repeated-span failures exceed allowance of 4 prompts (hf-009: rep 2: longest repeated span ratio 0.409 at or above harness ceiling over 20506 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-009: rep 2: longest repeated span ratio 0.409 at or above harness ceiling over 20506 chars))
16 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-000 | 88.51ms | 22.537s | 5120 | 40.80ms | 1605 gaps for 5120 tokens |
| hf-001 | 96.65ms | 23.023s | 5120 | 41.61ms | 1638 gaps for 5120 tokens |
| hf-002 | 160.67ms | 27.268s |
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 | C4 | 4 | 4 | 3.42 |
| 1 | 45.110s | C4 | 4 | 4 | 3.76 |
| 2 | 0.000s | C4 | 4 | 4 | 3.36 |
| 2 | 44.275s | C4 | 4 | 4 | 3.69 |
| 3 | 0.000s | C4 | 4 | 4 | 3.45 |
| 3 | 45.225s | C4 | 4 | 4 | 3.71 |
| 5120 |
| 41.57ms |
| 1863 gaps for 5120 tokens |
| hf-003 | 139.78ms | 24.100s | 5120 | 43.14ms | 1650 gaps for 5120 tokens |
| hf-004 | 154.86ms | 22.339s | 4882 | 41.01ms | 1529 gaps for 4882 tokens |
| hf-005 | 142.72ms | 19.819s | 3908 | 15.98ms | 1361 gaps for 3908 tokens |
| hf-006 | 90.76ms | 13.021s | 2917 | 15.15ms | 932 gaps for 2917 tokens |
| hf-007 | 90.64ms | 21.270s | 4396 | 40.80ms | 1517 gaps for 4396 tokens |
| hf-008 | 84.99ms | 22.387s | 5120 | 48.79ms | 1528 gaps for 5120 tokens |
| hf-009 | 86.32ms | 22.335s | 5120 | 48.91ms | 1535 gaps for 5120 tokens |
| hf-010 | 84.25ms | 24.668s | 5120 | 42.44ms | 1711 gaps for 5120 tokens |
| hf-011 | 59.56ms | 22.787s | 5120 | 46.08ms | 1615 gaps for 5120 tokens |
| hf-012 | 69.65ms | 21.617s | 5120 | 43.03ms | 1546 gaps for 5120 tokens |
| hf-013 | 84.14ms | 22.851s | 5120 | 16.38ms | 1599 gaps for 5120 tokens |
| hf-014 | 69.17ms | 12.620s | 2731 | 43.02ms | 896 gaps for 2731 tokens |
| hf-015 | 57.92ms | 21.736s | 4544 | 15.21ms | 1577 gaps for 4544 tokens |
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 | Baseline char-16 | Drop | Limit | Result |
|---|---|---|---|---|---|
| hf-000 | 0.7708 | 0.9784 | 0.2077 | 0.1000 | Failed rep 1: longest repeated span ratio 0.275 at or above harness ceiling over 15686 chars |
| hf-001 | 0.6661 | 0.7597 | 0.0935 | 0.1000 | Passed |
| hf-002 | 0.8329 | 0.8944 | 0.0614 | 0.1000 | Passed |
| hf-003 | 0.6368 | 0.9633 | 0.3266 | 0.1000 | Failed longest repeated span ratio 0.292 at or above harness ceiling over 22181 chars |
| hf-004 | 0.7886 | 0.9479 | 0.1593 | 0.1000 | Failed rep 3: longest repeated span ratio 0.256 at or above harness ceiling over 21728 chars |
| hf-005 | 0.8585 | 0.9048 | 0.0463 | 0.1000 | Passed |
| hf-006 | 0.9541 | 0.9607 | 0.0066 | 0.1000 | Passed |
| hf-007 | 0.8496 | 0.8991 | 0.0495 | 0.1000 | Passed |
| hf-008 | 0.5695 | 0.9360 | 0.3665 | 0.1000 | Failed longest repeated span ratio 0.345 at or above harness ceiling over 19915 chars |
| hf-009 | 0.5423 | 0.9555 | 0.4132 | 0.1000 | Failed longest repeated span ratio 0.409 at or above harness ceiling over 20506 chars |
| hf-010 | 0.7296 | 0.9513 | 0.2217 | 0.1000 | Failed distinct 16-gram ratio 0.730 is more than 0.10 below baseline 0.951 over 20820 chars |
| hf-011 | 0.6568 | 0.8237 | 0.1669 | 0.1000 | Failed distinct 16-gram ratio 0.657 is more than 0.10 below baseline 0.824 over 21697 chars |
| hf-012 | 0.7635 | 0.9790 | 0.2155 | 0.1000 | Failed distinct 16-gram ratio 0.764 is more than 0.10 below baseline 0.979 over 19348 chars |
| hf-013 | 0.6519 | 0.9074 | 0.2556 | 0.1000 | Failed distinct 16-gram ratio 0.652 is more than 0.10 below baseline 0.907 over 22345 chars |
| hf-014 | 0.9592 | 0.9737 | 0.0145 | 0.1000 | Passed |
| hf-015 | 0.9272 | 0.8589 | -0.0683 | 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-000 | 1 | 0.919431 | 1 | 0 |
| hf-006 | 1 | 0.88093 | 1 | 0 |
| hf-007 | 1 | 0.31014 | 1 | 0 |
| hf-001 | 1 | 0.202313 | 1 | 0 |
| hf-014 | 1 | 0.902302 | 1 | 0 |
| hf-011 | 1 | 0.103972 | 1 | 0 |
| hf-012 | 1 | 0.867259 | 1 | 0 |
| hf-015 | 1 | 0.249512 | 1 | 0 |
| hf-003 | 1 | 0.322659 | 1 | 0 |
| hf-004 | 1 | 0.561 | 1 | 0 |
| hf-005 | 1 | 0.297692 | 1 | 0 |
| hf-002 | 1 | 0.111747 | 1 | 0 |
| hf-008 | 1 | 0.380167 | 1 | 0 |
| hf-009 | 1 | 0.415164 | 1 | 0 |
| hf-010 | 1 | 0.302381 | 1 | 0 |
| hf-013 | 1 | 0.260907 | 1 | 0 |
| hf-006 | 2 | 0.88093 | 1 | 0 |
| hf-001 | 2 | 0.202313 | 1 | 0 |
| hf-007 | 2 | 0.31014 | 1 | 0 |
| hf-000 | 2 | 0.919431 | 1 | 0 |
| hf-014 | 2 | 0.902302 | 1 | 0 |
| hf-011 | 2 | 0.103972 | 1 | 0 |
| hf-012 | 2 | 0.867259 | 1 | 0 |
| hf-015 | 2 | 0.249512 | 1 | 0 |
| hf-005 | 2 | 0.297692 | 1 | 0 |
| hf-004 | 2 | 0.561 | 1 | 0 |
| hf-002 | 2 | 0.111747 | 1 | 0 |
| hf-003 | 2 | 0.322659 | 1 | 0 |
| hf-008 | 2 | 0.380167 | 1 | 0 |
| hf-009 | 2 | 0.415164 | 1 | 0 |
| hf-010 | 2 | 0.302381 | 1 | 0 |
| hf-013 | 2 | 0.260907 | 1 | 0 |
| hf-006 | 3 | 0.88093 | 1 | 0 |
| hf-007 | 3 | 0.31014 | 1 | 0 |
| hf-000 | 3 | 0.919431 | 1 | 0 |
| hf-001 | 3 | 0.202313 | 1 | 0 |
| hf-011 | 3 | 0.103972 | 1 | 0 |
| hf-012 | 3 | 0.867259 | 1 | 0 |
| hf-014 | 3 | 0.902302 | 1 | 0 |
| hf-015 | 3 | 0.249512 | 1 | 0 |
| hf-005 | 3 | 0.297692 | 1 | 0 |
| hf-004 | 3 | 0.561 | 1 | 0 |
| hf-003 | 3 | 0.322659 | 1 | 0 |
| hf-002 | 3 | 0.111747 | 1 | 0 |
| hf-009 | 3 | 0.415164 | 1 | 0 |
| hf-008 | 3 | 0.380167 | 1 | 0 |
| hf-010 | 3 | 0.302381 | 1 | 0 |
| hf-013 | 3 | 0.260907 | 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