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

Base model: Qwen/Qwen3.6-35B-A3Bmodel card · Vendor model card for the published adapter (9 Oct); the hosted Oct-4 checkpoint measured here is not stated to be identical.

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 & law49.0n=1616
Coding & software65.5n=382
Math & numbers9.7n=370
Finance & commerce44.4n=223
Support & operations42.4n=160
Everyday language72.4n=145
Safety & security59.0n=109

Use cases (TypeSafe categories)

Model routing66.8n=524
Legal & compliance66.3n=515
Customer support43.8n=240
E-commerce52.5n=119
Insurance claims42.2n=119
Risk assessment36.4n=118
Financial crime27.6n=101
Feature extraction32.7n=99
Lead generation53.0n=95
Recruiting23.0n=94
Knowledge graphs33.0n=94
LLM guardrails51.7n=93
Moderation61.4n=93
Code linting42.3n=90
Search & retrieval77.6n=90
Science28.3n=90
Advertising24.7n=88
Gaming0.0n=86
Demand forecasting0.0n=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.

Published source