SPX-CD Flash (SurdAI, hosted /v1/systemone, Oct-4 checkpoint)v1.7 · 10 s rule
Data: JevBench v1.8.18, published 2026-11-20 · method v1.7 (10 s rule), re-scored from the recorded per-decision times
Capability 74.3 · API offering, ranked on the API leaderboard
Last measured: 2026-10-06 · measurement release: v1.6.1
Licence not stated
intelligence
58.4
calibration
90.2
speed
79.2
cost
52.1
Composite (secondary)
66.6 · Not ranked on this board
Cost and measurement conditions
$0.039 per 1,000 decisions (estimated)
Operator's own public-beta overage tariff, conservative reading USD 0.04 per 1M input tokens, output USD 0 (the provider's /v1/models payload reports output_price "0"): three dated primary readings of the operator's own published overage tariff: 24 Sep 2026 provider console (flash 0.025, pro 0.08 per 1M input), 1 Oct 2026 docs page (flash 0.04, pro 0.02), 6 Oct 2026 docs page AND /v1/models payload agreeing (flash 0.02, pro 0.04). Sources conflict, so the per-model MAXIMUM is used, which is the published fastino-gliner-2-5-decide precedent ("published sources conflict ... conservative higher"). Today's agreeing pair would be USD 0.02/M, i.e. half this row's cost. No base-model floor applies: the submitter states the base model stays sealed until a later open release, so no base model exists to reference. Priced on usage.input_tokens as the provider reports them. The provider also reports billable_input_tokens = input_tokens / 2 on every single item (297/297 of the public set, exactly 2.0): its default effort 2 renders the prompt twice and its docs bundle the second pass free during public beta ("default effort 2 is included at the single-pass input price"). That bundle is a public-beta promotion, and TASK.md forbids a free or promotional tier setting the price, so the two passes actually consumed are charged. The operator's own billed figure is exactly half of this row's cost
p50 latency: 1.0 s
none (API)
measured 2026-10-06 on the live v1.6.0 S u P (1,500 rows) under the published 5 Oct 2026 full-set amendment, through the standard full-set API lane (run_api_full_v161.py, rotation.py expose --full-set logged 1,200 sealed items to provider 'surd' before the first request); stock jevbench.adapters.typesafe with an endpoint override only, reasoning at the provider default, one request at a time, no retries; add-requests run 53, benchmarkheaven.com/submit ref 3FF00545
Measured latency over 1,500 decisions: p50 1.015 s · p95 1.188 s
0 decisions over 10 s.
A decision that takes longer than 10 seconds (measured time) counts as a wrong answer and as zero calibration for that item: each type's calibration is multiplied by the share of its decisions answered within 10 s. The limit uses the measured time (raw). The displayed adjusted time for self-hosted rows (2 × + 0.15 s) is an assumption and is not used for the limit.
Breakdowns (not part of the score)
Chance-corrected competence (0 = chance, 100 = perfect) by category on S+P+L1+L2+L3. Raw values, not equated; the same cells feed the compare view.
Capability by subject topic
| Rules, policy & law | 49.0 | n=1616 |
|---|---|---|
| Coding & software | 65.5 | n=382 |
| Math & numbers | 9.7 | n=370 |
| Finance & commerce | 44.4 | n=223 |
| Support & operations | 42.4 | n=160 |
| Everyday language | 72.4 | n=145 |
| Safety & security | 59.0 | n=109 |
Use cases (TypeSafe categories)
| Model routing | 66.8 | n=524 |
|---|---|---|
| Legal & compliance | 66.3 | n=515 |
| Customer support | 43.8 | n=240 |
| E-commerce | 52.5 | n=119 |
| Insurance claims | 42.2 | n=119 |
| Risk assessment | 36.4 | n=118 |
| Financial crime | 27.6 | n=101 |
| Feature extraction | 32.7 | n=99 |
| Lead generation | 53.0 | n=95 |
| Recruiting | 23.0 | n=94 |
| Knowledge graphs | 33.0 | n=94 |
| LLM guardrails | 51.7 | n=93 |
| Moderation | 61.4 | n=93 |
| Code linting | 42.3 | n=90 |
| Search & retrieval | 77.6 | n=90 |
| Science | 28.3 | n=90 |
| Advertising | 24.7 | n=88 |
| Gaming | 0.0 | n=86 |
| Demand forecasting | 0.0 | n=83 |
Cells need at least 30 answered items; † fewer than 30 (indicative only; drawn as hollow, lighter points on the compare radars).
JevBench v1.6.43 values (method v1.6, before the 10 s rule)
Capability 74.32 · Composite 66.68 · rank #44 on the all-systems board · #21 API
intelligence 58.43 · calibration 90.20 · speed 79.39 · cost 52.11
v1.6 speed basis (124 items): p50 0.980 s · p95 1.173 s
These figures are kept for comparison. The current figures above are re-scored under the 10 s rule from the recorded per-decision times and replace them.