Round score
—
degenerate output (baseline-relative repetition failures exceed allowance of 4 prompts (hf-011: distinct 16-gram ratio 0.573 is more than 0.10 below baseline 0.824 over 21174 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 (baseline-relative repetition failures exceed allowance of 4 prompts (hf-011: distinct 16-gram ratio 0.573 is more than 0.10 below baseline 0.824 over 21174 chars))
16 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-000 | 87.19ms | 22.665s | 5120 | 41.27ms | 1617 gaps for 5120 tokens |
| hf-001 | 99.04ms | 23.833s | 5120 | 41.28ms | 1697 gaps for 5120 tokens |
| hf-002 | 95.29ms | 23.675s |
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 | 3.46 |
| 1 | 44.607s | C4 | 4 | 4 | 3.79 |
| 2 | 0.000s | C4 | 4 | 4 | 3.26 |
| 2 | 44.279s | C4 | 4 | 4 | 3.68 |
| 3 | 0.000s | C4 | 4 | 4 | 3.79 |
| 3 | 45.678s | C4 | 4 | 4 | 3.92 |
| 4183 |
| 53.41ms |
| 1624 gaps for 4183 tokens |
| hf-003 | 134.43ms | 23.934s | 4513 | 41.72ms | 1640 gaps for 4513 tokens |
| hf-004 | 131.15ms | 23.456s | 5120 | 17.30ms | 1611 gaps for 5120 tokens |
| hf-005 | 140.15ms | 23.775s | 5120 | 40.68ms | 1628 gaps for 5120 tokens |
| hf-006 | 91.23ms | 5.861s | 1303 | 15.05ms | 418 gaps for 1303 tokens |
| hf-007 | 90.55ms | 21.635s | 4435 | 39.96ms | 1546 gaps for 4435 tokens |
| hf-008 | 84.97ms | 21.648s | 5120 | 42.95ms | 1480 gaps for 5120 tokens |
| hf-009 | 83.13ms | 24.285s | 5120 | 42.08ms | 1670 gaps for 5120 tokens |
| hf-010 | 83.97ms | 24.806s | 4709 | 42.12ms | 1732 gaps for 4709 tokens |
| hf-011 | 70.34ms | 22.273s | 5120 | 43.27ms | 1581 gaps for 5120 tokens |
| hf-012 | 69.45ms | 22.620s | 5120 | 43.28ms | 1616 gaps for 5120 tokens |
| hf-013 | 86.06ms | 21.941s | 4367 | 16.21ms | 1509 gaps for 4367 tokens |
| hf-014 | 56.42ms | 17.011s | 3787 | 42.53ms | 1235 gaps for 3787 tokens |
| hf-015 | 63.38ms | 20.426s | 4342 | 16.20ms | 1504 gaps for 4342 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 | 0.9102 | 0.9784 | 0.0682 | 0.1000 | Passed |
| hf-001 | 0.7840 | 0.7597 | -0.0243 | 0.1000 | Failed rep 2: longest repeated span ratio 0.255 at or above harness ceiling over 23509 chars |
| hf-002 | 0.9726 | 0.8944 | -0.0782 | 0.1000 | Passed |
| hf-003 | 0.9659 | 0.9633 | -0.0025 | 0.1000 | Passed |
| hf-004 | 0.7654 | 0.9479 | 0.1825 | 0.1000 | Failed distinct 16-gram ratio 0.765 is more than 0.10 below baseline 0.948 over 19976 chars |
| hf-005 | 0.6970 | 0.9048 | 0.2078 | 0.1000 | Failed distinct 16-gram ratio 0.697 is more than 0.10 below baseline 0.905 over 20951 chars |
| hf-006 | 0.9129 | 0.9607 | 0.0478 | 0.1000 | Passed |
| hf-007 | 0.8939 | 0.8991 | 0.0052 | 0.1000 | Passed |
| hf-008 | 0.5081 | 0.9360 | 0.4279 | 0.1000 | Failed distinct 16-gram ratio 0.508 is more than 0.10 below baseline 0.936 over 20541 chars |
| hf-009 | 0.7725 | 0.9555 | 0.1830 | 0.1000 | Failed rep 3: longest repeated span ratio 0.378 at or above harness ceiling over 21663 chars |
| hf-010 | 0.9526 | 0.9513 | -0.0013 | 0.1000 | Passed |
| hf-011 | 0.5726 | 0.8237 | 0.2511 | 0.1000 | Failed rep 1: longest repeated span ratio 0.269 at or above harness ceiling over 19689 chars |
| hf-012 | 0.8063 | 0.9790 | 0.1728 | 0.1000 | Failed distinct 16-gram ratio 0.806 is more than 0.10 below baseline 0.979 over 21478 chars |
| hf-013 | 0.8191 | 0.9074 | 0.0883 | 0.1000 | Passed |
| hf-014 | 0.8575 | 0.9737 | 0.1162 | 0.1000 | Failed distinct 16-gram ratio 0.858 is more than 0.10 below baseline 0.974 over 16553 chars |
| hf-015 | 0.9307 | 0.8589 | -0.0718 | 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-006 | 1 | 0.88093 | 1 | 0 |
| hf-001 | 1 | 0.202313 | 1 | 0 |
| hf-007 | 1 | 0.31014 | 1 | 0 |
| hf-000 | 1 | 0.919431 | 1 | 0 |
| hf-011 | 1 | 0.103972 | 1 | 0 |
| hf-014 | 1 | 0.902302 | 1 | 0 |
| hf-015 | 1 | 0.249512 | 1 | 0 |
| hf-012 | 1 | 0.867259 | 1 | 0 |
| hf-003 | 1 | 0.322659 | 1 | 0 |
| hf-005 | 1 | 0.297692 | 1 | 0 |
| hf-004 | 1 | 0.561 | 1 | 0 |
| hf-002 | 1 | 0.111747 | 1 | 0 |
| hf-008 | 1 | 0.380167 | 1 | 0 |
| hf-013 | 1 | 0.260907 | 1 | 0 |
| hf-009 | 1 | 0.415164 | 1 | 0 |
| hf-010 | 1 | 0.302381 | 1 | 0 |
| hf-006 | 2 | 0.88093 | 1 | 0 |
| hf-007 | 2 | 0.31014 | 1 | 0 |
| hf-000 | 2 | 0.919431 | 1 | 0 |
| hf-001 | 2 | 0.202313 | 1 | 0 |
| hf-011 | 2 | 0.103972 | 1 | 0 |
| hf-012 | 2 | 0.867259 | 1 | 0 |
| hf-014 | 2 | 0.902302 | 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-007 | 3 | 0.31014 | 1 | 0 |
| hf-000 | 3 | 0.919431 | 1 | 0 |
| hf-006 | 3 | 0.88093 | 1 | 0 |
| hf-001 | 3 | 0.202313 | 1 | 0 |
| hf-011 | 3 | 0.103972 | 1 | 0 |
| hf-014 | 3 | 0.902302 | 1 | 0 |
| hf-012 | 3 | 0.867259 | 1 | 0 |
| hf-015 | 3 | 0.249512 | 1 | 0 |
| hf-004 | 3 | 0.561 | 1 | 0 |
| hf-002 | 3 | 0.111747 | 1 | 0 |
| hf-003 | 3 | 0.322659 | 1 | 0 |
| hf-005 | 3 | 0.297692 | 1 | 0 |
| hf-008 | 3 | 0.380167 | 1 | 0 |
| hf-013 | 3 | 0.260907 | 1 | 0 |
| hf-009 | 3 | 0.415164 | 1 | 0 |
| hf-010 | 3 | 0.302381 | 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