Report · resources

Answer quality

Ornith-1.5-35B-A3B · NVFP4 variant · NVIDIA NGC vLLM 0.29

Measured results / Answer quality / Run 70d5791f1fec47958088dcc3

Measured 2026-10-07 05:52 UTC · Record date 2026-10-07

Partial. 71/130 tasks71/124 API cases

First word afterttft_median_s · s
0.06 sper person · median · sample count not recorded

Answer checks

71/130 tasks71/124 API cases

API suite category outcomes
CategoryPassed / totalSkippedRun
api
5/8
0
code
16/16
0
format
7/12
0
multi_turn
1/8
0
multilingual
6/6
0
numeric
15/16
0
reasoning
0/4
0
refusal
6/6
0
structured_extraction
5/16
0
supplied_context
2/16
0
tools
8/8
0
untrusted_text
0/8
0
vision
0/0
4

Method

Deterministic API suite core-v1; SHA256 42c4dc34a066f791a62c9b1dbeb97943988c746309a43a464f0417a02ae9f1da; no model judge; no retries; unchanged endpoint cache; latency excludes local grading; paired calls counted separately. Client concurrency; configured sequence limit 20.

Limits

Bounded fictional tasks only. Unsupported cases are separately counted, never passes. Original publisher name with variant; exact variant repository and revision retained privately. Not customer acceptance.

What did not work

  • 71/130 tasks passed.
  • 71/124 API cases passed.

What ran

Exact identity

Original publisher model
Ornith-1.5-35B-A3B
Publisher revision
not recorded
Variant · format · precision
NVFP4 variant · safetensors · NVFP4
Weights SHA-256
not recorded
Engine · version · feature
NVIDIA NGC vLLM · 0.29.0+5013de39.dev · plain
Hardware
NVIDIA GB10, 128 GB unified memory
Harness / workload
keep-api-suite-run-v1 · 1
Workload suite · version
core-v1 · 1
Harness SHA-256
not recorded
Fixture SHA-256
42c4dc34a066f791a62c9b1dbeb97943988c746309a43a464f0417a02ae9f1da

Workload shape

People in this run
1
Configured window (tokens)
262144
KV cache precision
fp8
Feature
plain

Full reproduction pack available to customers and evaluators on request

All recorded numbers

Metric definitions, scope and statistics
All aggregate numeric result fields in this run
MetricValueScopeStatisticSample countBasis / source fieldRun
skipped cases
4.00 count
machine total
single
not recorded
skipped_cases
correctness failures
50.00 count
machine total
single
not recorded
correctness_failures
ttft median s
0.06 s
per person
median
not recorded
ttft_median_s
workload total
130.00 count
machine total
single
not recorded
workload_total
workload passed
71.00 count
machine total
single
not recorded
workload_passed
api cases passed
71.00 count
machine total
single
not recorded
api_cases_passed
ttft p95 s
0.11 s
per person
p95
not recorded
ttft_p95_s
completion p95 s
0.77 s
per person
p95
not recorded
completion_p95_s
api cases total
124.00 count
machine total
single
not recorded
api_cases_total
completion median s
0.23 s
per person
median
not recorded
completion_median_s
completeness failures
11.00 count
machine total
single
not recorded
completeness_failures

Data and citation

Skilak Keep evidence, run 70d5791f1fec47958088dcc3, measured 2026-10-07T05:52:52.779398+00:00.
https://skilak.ai/keep/resources/evidence/r/70d5791f1fec47958088dcc3

Ready to scope it?

Start with one workload.

Tell us who uses it, what it can read, and what must stay inside. We will map the build.