- Writing speed, each persondecode_tps · tok/s
- 5.95 tok/sper person · median of 20
- First word afterttft_median_s · s
- 113.84 sper person · median of 20
- Slowest first wordttft_max_s · s
- 161.93 sper person · max of 20
- Machine totalaggregate_decode_tps · tok/s
- 71.65 tok/smachine total · single · sample count not recorded
- Machine total including first-word waitaggregate_e2e_tps · tok/s
- 50.81 tok/smachine total · single · sample count not recorded
- Everyone answered inwall_seconds · s
- 201.55 smachine total · single · sample count not recorded
- Peak memory, whole hostpeak_host_unavailable_gib · GiB
- 94.15 GiBmachine total · max · sample count not recorded
Runs on this setup
Earlier runs keep their own engine versions and outcomes. Workload shapes stay separate.
History and measured sweep
| Date | Shape | Each person · median | Machine total | First word · median | Result | Run |
|---|---|---|---|---|---|---|
2026-10-07 | 20 people | 5.95 tok/s | 71.65 tok/s | 113.84 s | Failed | |
2026-10-07 | 16 people | 7.51 tok/s | 79.26 tok/s | 93.56 s | Failed | |
2026-10-07 | 8 people | 16.69 tok/s | 125.33 tok/s | 54.30 s | Failed | |
2026-10-07 | 1 people | 67.26 tok/s | 67.26 tok/s | 10.06 s | Passed |
Each person in this run
First-word wait against writing speed after that word, including pauses. Earlier streams can pause while other people’s prompts are read. The table preserves filled input, cached-token counts and each person’s checks.
Per-person table · all measured request rows
| Person | Filled input | Cached tokens | Output | First word | Writing after first word | Total time | Checks | Run |
|---|---|---|---|---|---|---|---|---|
1 | 40,105 | unknown | 512 | 148.91 s | 9.79 tok/sone person · includes waits | 201.12 s | 3/3 Hidden facts found · completed · checks passed | |
2 | 40,101 | unknown | 512 | 93.12 s | 4.81 tok/sone person · includes waits | 199.44 s | 3/3 Hidden facts found · completed · checks passed | |
3 | 40,099 | unknown | 512 | 62.21 s | 3.76 tok/sone person · includes waits | 198.20 s | 0/3 Hidden facts found · completed · checks missed | |
4 | 40,103 | unknown | 512 | 93.12 s | 4.81 tok/sone person · includes waits | 199.44 s | 0/3 Hidden facts found · completed · checks missed | |
5 | 40,105 | unknown | 512 | 119.84 s | 6.35 tok/sone person · includes waits | 200.29 s | 0/3 Hidden facts found · completed · checks missed | |
6 | 40,102 | unknown | 512 | 126.13 s | 6.87 tok/sone person · includes waits | 200.48 s | 0/3 Hidden facts found · completed · checks missed | |
7 | 40,102 | unknown | 512 | 60.64 s | 3.72 tok/sone person · includes waits | 198.11 s | 3/3 Hidden facts found · completed · checks passed | |
8 | 40,103 | unknown | 512 | 62.21 s | 3.76 tok/sone person · includes waits | 198.20 s | 3/3 Hidden facts found · completed · checks passed | |
9 | 40,104 | unknown | 512 | 107.84 s | 5.55 tok/sone person · includes waits | 199.94 s | 0/3 Hidden facts found · completed · checks missed | |
10 | 40,099 | unknown | 512 | 161.93 s | 12.90 tok/sone person · includes waits | 201.55 s | 3/3 Hidden facts found · completed · checks passed | |
11 | 40,105 | unknown | 512 | 137.91 s | 8.12 tok/sone person · includes waits | 200.80 s | 3/3 Hidden facts found · completed · checks passed | |
12 | 40,106 | unknown | 512 | 161.59 s | 12.79 tok/sone person · includes waits | 201.53 s | 0/3 Hidden facts found · completed · checks missed | |
13 | 40,102 | unknown | 512 | 58.91 s | 3.67 tok/sone person · includes waits | 198.03 s | 3/3 Hidden facts found · completed · checks passed | |
14 | 40,104 | unknown | 512 | 158.88 s | 12.01 tok/sone person · includes waits | 201.43 s | 0/3 Hidden facts found · completed · checks missed | |
15 | 40,102 | unknown | 512 | 145.75 s | 9.25 tok/sone person · includes waits | 201.02 s | 3/3 Hidden facts found · completed · checks passed | |
16 | 40,105 | unknown | 512 | 153.57 s | 10.71 tok/sone person · includes waits | 201.26 s | 3/3 Hidden facts found · completed · checks passed | |
17 | 40,099 | unknown | 512 | 91.53 s | 4.74 tok/sone person · includes waits | 199.38 s | 3/3 Hidden facts found · completed · checks passed | |
18 | 40,097 | unknown | 512 | 124.63 s | 6.74 tok/sone person · includes waits | 200.44 s | 3/3 Hidden facts found · completed · checks passed | |
19 | 40,105 | unknown | 512 | 62.21 s | 3.76 tok/sone person · includes waits | 198.20 s | 3/3 Hidden facts found · completed · checks passed | |
20 | 40,102 | unknown | 512 | 62.21 s | 3.76 tok/sone person · includes waits | 198.20 s | 3/3 Hidden facts found · completed · checks passed |
Per-person table · all measured request rows
| Person | Filled input | Cached tokens | Output | First word | Writing after first word | Total time | Checks | Run |
|---|---|---|---|---|---|---|---|---|
1 | 40,105 | unknown | 512 | 148.91 s | 9.79 tok/sone person · includes waits | 201.12 s | 3/3 Hidden facts found · completed · checks passed | |
2 | 40,101 | unknown | 512 | 93.12 s | 4.81 tok/sone person · includes waits | 199.44 s | 3/3 Hidden facts found · completed · checks passed | |
3 | 40,099 | unknown | 512 | 62.21 s | 3.76 tok/sone person · includes waits | 198.20 s | 0/3 Hidden facts found · completed · checks missed | |
4 | 40,103 | unknown | 512 | 93.12 s | 4.81 tok/sone person · includes waits | 199.44 s | 0/3 Hidden facts found · completed · checks missed | |
5 | 40,105 | unknown | 512 | 119.84 s | 6.35 tok/sone person · includes waits | 200.29 s | 0/3 Hidden facts found · completed · checks missed | |
6 | 40,102 | unknown | 512 | 126.13 s | 6.87 tok/sone person · includes waits | 200.48 s | 0/3 Hidden facts found · completed · checks missed | |
7 | 40,102 | unknown | 512 | 60.64 s | 3.72 tok/sone person · includes waits | 198.11 s | 3/3 Hidden facts found · completed · checks passed | |
8 | 40,103 | unknown | 512 | 62.21 s | 3.76 tok/sone person · includes waits | 198.20 s | 3/3 Hidden facts found · completed · checks passed | |
9 | 40,104 | unknown | 512 | 107.84 s | 5.55 tok/sone person · includes waits | 199.94 s | 0/3 Hidden facts found · completed · checks missed | |
10 | 40,099 | unknown | 512 | 161.93 s | 12.90 tok/sone person · includes waits | 201.55 s | 3/3 Hidden facts found · completed · checks passed | |
11 | 40,105 | unknown | 512 | 137.91 s | 8.12 tok/sone person · includes waits | 200.80 s | 3/3 Hidden facts found · completed · checks passed | |
12 | 40,106 | unknown | 512 | 161.59 s | 12.79 tok/sone person · includes waits | 201.53 s | 0/3 Hidden facts found · completed · checks missed | |
13 | 40,102 | unknown | 512 | 58.91 s | 3.67 tok/sone person · includes waits | 198.03 s | 3/3 Hidden facts found · completed · checks passed | |
14 | 40,104 | unknown | 512 | 158.88 s | 12.01 tok/sone person · includes waits | 201.43 s | 0/3 Hidden facts found · completed · checks missed | |
15 | 40,102 | unknown | 512 | 145.75 s | 9.25 tok/sone person · includes waits | 201.02 s | 3/3 Hidden facts found · completed · checks passed | |
16 | 40,105 | unknown | 512 | 153.57 s | 10.71 tok/sone person · includes waits | 201.26 s | 3/3 Hidden facts found · completed · checks passed | |
17 | 40,099 | unknown | 512 | 91.53 s | 4.74 tok/sone person · includes waits | 199.38 s | 3/3 Hidden facts found · completed · checks passed | |
18 | 40,097 | unknown | 512 | 124.63 s | 6.74 tok/sone person · includes waits | 200.44 s | 3/3 Hidden facts found · completed · checks passed | |
19 | 40,105 | unknown | 512 | 62.21 s | 3.76 tok/sone person · includes waits | 198.20 s | 3/3 Hidden facts found · completed · checks passed | |
20 | 40,102 | unknown | 512 | 62.21 s | 3.76 tok/sone person · includes waits | 198.20 s | 3/3 Hidden facts found · completed · checks passed |
Answer checks
39/60 Hidden facts found13/20 probes20/20 request checks
Method
team-load-v1; distinct generated 40000-token coding contexts plus fresh nonce prefixes; synchronized streams; temperature zero; thinking off; min_tokens=max_tokens=512; separate cold hidden facts probes; no retries.
Limits
Finite lab cohort; configured 262144 context differs from measured inputs. Aggregate uses first-output to final-completion window. Whole-host memory sampled during speed only; missing counters remain unassessed. Broader coding quality and delivery acceptance unassessed.
What did not work
- 39/60 Hidden facts found.
- 13/20 probes passed.
What ran
Exact identity
- Original publisher model
- Ornith-1.5-35B-A3B
- Publisher revision
10fbf86fed7ecee4a061f8b499a618f46001cac1- Variant · format · precision
- NVFP4 variant · safetensors · nvfp4
- Weights SHA-256
648fe83171485f4be03ea58d86089e088c94c2a3dc88922233f9002f30d8bc8b8303cef7d375021d69dcafc60d3fad5f8186995b18b0db5e2a609aadeb8a4f51cb5c5978721a1e87406ae68f1cd5a855326e40ff8bc13832644c392115336987- Engine · version · feature
- NVIDIA NGC vLLM ·
0.29.0+5013de39.dev· plain - Hardware
- NVIDIA GB10, 128 GB unified memory
- Harness / workload
keep-team-load-v1 · 1- Workload suite · version
not recorded- Harness SHA-256
not recorded- Fixture SHA-256
e2097959b1ca0142f2b93edc3ec411e474c0a6622800dd247af7a71bd9c39e83
Workload shape
- People in this run
- 20
- Configured window (tokens)
- 262144
- Configured window (tokens)
- 262144
- KV cache precision
- fp8
- Output token ceiling
- 512
- Feature
- plain
- Thinking
- off
Full reproduction pack available to customers and evaluators on request
All recorded numbers
Metric definitions, scope and statistics
| Metric | Value | Scope | Statistic | Sample count | Basis / source field | Run |
|---|---|---|---|---|---|---|
wall seconds | 201.55 s | machine total | single | not recorded | wall_seconds | |
ttft median s | 113.84 s | per person | median | 20 | ttft_median_s | |
hidden facts total | 60.00 count | machine total | single | not recorded | needle_total | |
ttft max s | 161.93 s | per person | max | 20 | ttft_max_s | |
requests ok | 20.00 count | machine total | single | not recorded | requests_ok | |
hidden facts correct | 39.00 count | machine total | single | not recorded | needle_correct | |
preemptions | 0.00 count | machine total | single | not recorded | preemptions | |
decode overlap | 20.00 count | machine total | single | not recorded | decode_overlap | |
aggregate concurrency | 20.00 count | machine total | single | not recorded | aggregate_concurrency | |
requests total | 20.00 count | machine total | single | not recorded | requests_total | |
correctness probes passed | 13.00 count | machine total | single | not recorded | correctness_probes_passed | |
aggregate decode tps | 71.65 tok/s | machine total | single | not recorded | aggregate_tps | |
aggregate e2e tps | 50.81 tok/s | machine total | single | not recorded | aggregate_end_to_end_tps | |
correctness probes total | 20.00 count | machine total | single | not recorded | correctness_probes_total | |
decode tps | 6.89 tok/s | per person | mean | 20 | per_request_decode_tps | |
forced output tokens | 512.00 tokens | machine total | single | not recorded | forced_output_tokens | |
peak host unavailable gib | 94.15 GiB | machine total | max | not recorded | peak_host_unavailable_gib | |
decode tps | 5.95 tok/s | per person | median | 20 | per_person_decode_median_tps |
Data and citation
Skilak Keep evidence, run e51d5cbb032741a59bd7cde5, measured 2026-10-07T05:50:54.427704+00:00. https://skilak.ai/keep/resources/evidence/r/e51d5cbb032741a59bd7cde5
