Round score
0.6964
weighted tier speedup after failure cap and deduction
Eligible requests
16
trusted baseline exclusions removed
Failed eligible requests
0
each request counted once
Raw weighted speedup
+69.64%
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
No request failures: eligible speedup equals raw weighted speedup.
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.
16 prompts
| Prompt | Diagnostic speedup | Baseline | Candidate | Aligned output | Diagnostic / failure |
|---|---|---|---|---|---|
| hf-009 | — | — | — | 4532 | Per-token timing unavailable (not a request failure) |
| hf-002 | — | — | — | 4294 | Per-token timing unavailable (not a request failure) |
| hf-007 | — | — | — |
16 requests
| Request | TTFT | Total | Tokens | Slowest gap | Stream |
|---|---|---|---|---|---|
| hf-000 | 156.00ms | 21.957s | 4871 | 46.86ms | 1706 gaps for 4871 tokens |
| hf-001 | 121.47ms | 23.518s | 5120 | 49.93ms | 1825 gaps for 5120 tokens |
| hf-002 | 114.86ms | 23.248s |
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 | 3.79 |
| 1 | 44.378s | C4 | 4 | 4 | 3.85 |
| 2 | 0.000s | C4 | 4 | 4 | 3.78 |
| 2 | 44.149s | C4 | 4 | 4 | 3.39 |
| 3 | 0.000s | C4 | 4 | 4 | 3.90 |
| 3 | 44.517s | C4 | 4 | 4 | 3.88 |
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 |
|---|---|---|---|---|---|---|
| 8k | 8 | 50% | 145.786s | 44.376s | +69.56% | +34.78% |
| 16k | 8 | 50% | 152.706s | 46.231s | +69.73% | +34.86% |
| 5120 |
| Per-token timing unavailable (not a request failure) |
| hf-010 | — | — | — | 5120 | Per-token timing unavailable (not a request failure) |
| hf-012 | — | — | — | 4119 | Per-token timing unavailable (not a request failure) |
| hf-013 | — | — | — | 5120 | Per-token timing unavailable (not a request failure) |
| hf-014 | — | — | — | 5053 | Per-token timing unavailable (not a request failure) |
| hf-015 | — | — | — | 4923 | Per-token timing unavailable (not a request failure) |
| hf-003 | — | — | — | 4313 | Per-token timing unavailable (not a request failure) |
| hf-004 | — | — | — | 4559 | Per-token timing unavailable (not a request failure) |
| hf-001 | — | — | — | 5120 | Per-token timing unavailable (not a request failure) |
| hf-000 | — | — | — | 4871 | Per-token timing unavailable (not a request failure) |
| hf-005 | — | — | — | 4899 | Per-token timing unavailable (not a request failure) |
| hf-008 | — | — | — | 4946 | Per-token timing unavailable (not a request failure) |
| hf-006 | — | — | — | 5120 | Per-token timing unavailable (not a request failure) |
| hf-011 | — | — | — | 4971 | Per-token timing unavailable (not a request failure) |
| 5120 |
| 43.95ms |
| 1863 gaps for 5120 tokens |
| hf-003 | 159.61ms | 23.551s | 5120 | 46.90ms | 1827 gaps for 5120 tokens |
| hf-004 | 159.48ms | 21.112s | 4797 | 15.23ms | 1643 gaps for 4797 tokens |
| hf-005 | 98.33ms | 22.700s | 5120 | 46.65ms | 1763 gaps for 5120 tokens |
| hf-006 | 92.86ms | 22.863s | 5120 | 43.40ms | 1819 gaps for 5120 tokens |
| hf-007 | 109.60ms | 19.814s | 5120 | 45.59ms | 1591 gaps for 5120 tokens |
| hf-008 | 108.86ms | 23.183s | 5120 | 14.64ms | 1825 gaps for 5120 tokens |
| hf-009 | 124.01ms | 20.671s | 4538 | 44.28ms | 1662 gaps for 4538 tokens |
| hf-010 | 122.77ms | 21.023s | 5120 | 44.28ms | 1688 gaps for 5120 tokens |
| hf-011 | 77.89ms | 22.479s | 5120 | 17.04ms | 1767 gaps for 5120 tokens |
| hf-012 | 70.01ms | 21.322s | 5120 | 41.00ms | 1710 gaps for 5120 tokens |
| hf-013 | 77.34ms | 22.632s | 5120 | 42.15ms | 1827 gaps for 5120 tokens |
| hf-014 | 79.81ms | 20.493s | 5120 | 41.49ms | 1650 gaps for 5120 tokens |
| hf-015 | 63.85ms | 20.983s | 5120 | 17.00ms | 1711 gaps for 5120 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 | 0.9438 | 0.9835 | 0.0398 | 0.1000 | Passed |
| hf-001 | 0.9579 | 0.9535 | -0.0044 | 0.1000 | Passed |
| hf-002 | 0.9123 | 0.8763 | -0.0361 | 0.1000 | Passed |
| hf-003 | 0.8925 | 0.8895 | -0.0031 | 0.1000 | Passed |
| hf-004 | 0.9570 | 0.9121 | -0.0449 | 0.1000 | Passed |
| hf-005 | 0.9473 | 0.9532 | 0.0059 | 0.1000 | Passed |
| hf-006 | 0.9286 | 0.9494 | 0.0208 | 0.1000 | Passed |
| hf-007 | 0.6737 | 0.9088 | 0.2351 | 0.1000 | Failed distinct 16-gram ratio 0.674 is more than 0.10 below baseline 0.909 over 20841 chars |
| hf-008 | 0.9476 | 0.9557 | 0.0081 | 0.1000 | Passed |
| hf-009 | 0.9429 | 0.8497 | -0.0932 | 0.1000 | Passed |
| hf-010 | 0.9061 | 0.9712 | 0.0651 | 0.1000 | Passed |
| hf-011 | 0.9148 | 0.8315 | -0.0832 | 0.1000 | Passed |
| hf-012 | 0.7830 | 0.9198 | 0.1367 | 0.1000 | Failed distinct 16-gram ratio 0.783 is more than 0.10 below baseline 0.920 over 20965 chars |
| hf-013 | 0.9286 | 0.9577 | 0.0291 | 0.1000 | Passed |
| hf-014 | 0.7697 | 0.9436 | 0.1738 | 0.1000 | Failed distinct 16-gram ratio 0.770 is more than 0.10 below baseline 0.944 over 21443 chars |
| hf-015 | 0.8999 | 0.9561 | 0.0561 | 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-009 | 1 | 0.208989 | 1 | 0 |
| hf-007 | 1 | 0.417374 | 1 | 0 |
| hf-010 | 1 | 0.855638 | 1 | 0 |
| hf-002 | 1 | 0.189667 | 1 | 0 |
| hf-012 | 1 | 0.325767 | 1 | 0 |
| hf-014 | 1 | 0.590278 | 1 | 0 |
| hf-013 | 1 | 0.566642 | 1 | 0 |
| hf-015 | 1 | 0.591114 | 1 | 0 |
| hf-004 | 1 | 0.84741 | 1 | 0 |
| hf-000 | 1 | 0.91753 | 1 | 0 |
| hf-001 | 1 | 0.486939 | 1 | 0 |
| hf-003 | 1 | 0.159301 | 1 | 0 |
| hf-005 | 1 | 0.743609 | 1 | 0 |
| hf-006 | 1 | 0.418659 | 1 | 0 |
| hf-011 | 1 | 0.433119 | 1 | 0 |
| hf-008 | 1 | 0.355751 | 1 | 0 |
| hf-007 | 2 | 0.417374 | 1 | 0 |
| hf-009 | 2 | 0.208989 | 1 | 0 |
| hf-010 | 2 | 0.855638 | 1 | 0 |
| hf-002 | 2 | 0.189667 | 1 | 0 |
| hf-012 | 2 | 0.325767 | 1 | 0 |
| hf-014 | 2 | 0.590278 | 1 | 0 |
| hf-013 | 2 | 0.566642 | 1 | 0 |
| hf-015 | 2 | 0.591114 | 1 | 0 |
| hf-000 | 2 | 0.91753 | 1 | 0 |
| hf-005 | 2 | 0.743609 | 1 | 0 |
| hf-004 | 2 | 0.84741 | 1 | 0 |
| hf-001 | 2 | 0.486939 | 1 | 0 |
| hf-003 | 2 | 0.159301 | 1 | 0 |
| hf-006 | 2 | 0.418659 | 1 | 0 |
| hf-008 | 2 | 0.355751 | 1 | 0 |
| hf-011 | 2 | 0.433119 | 1 | 0 |
| hf-010 | 3 | 0.855638 | 1 | 0 |
| hf-007 | 3 | 0.417374 | 1 | 0 |
| hf-009 | 3 | 0.208989 | 1 | 0 |
| hf-002 | 3 | 0.189667 | 1 | 0 |
| hf-014 | 3 | 0.590278 | 1 | 0 |
| hf-012 | 3 | 0.325767 | 1 | 0 |
| hf-013 | 3 | 0.566642 | 1 | 0 |
| hf-015 | 3 | 0.591114 | 1 | 0 |
| hf-004 | 3 | 0.84741 | 1 | 0 |
| hf-000 | 3 | 0.91753 | 1 | 0 |
| hf-001 | 3 | 0.486939 | 1 | 0 |
| hf-003 | 3 | 0.159301 | 1 | 0 |
| hf-005 | 3 | 0.743609 | 1 | 0 |
| hf-006 | 3 | 0.418659 | 1 | 0 |
| hf-011 | 3 | 0.433119 | 1 | 0 |
| hf-008 | 3 | 0.355751 | 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