SPX-CD-Omni (SurdAI, google/gemma-4-12B-it + LoRA r32, one forward pass, self-hosted)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 68.1 · rank #98 of 251 on the open-weights board

Last measured: 2026-10-06 · measurement release: v1.6.1

apache-2.0

Base model: google/gemma-4-12B-itsource

intelligence

48.8

calibration

87.5

speed

89.1

cost

68.7

Composite (secondary)

66.0 · Composite rank #105

Cost and measurement conditions

$0.011 per 1,000 decisions (estimated)

GPU-time estimate from v1.8.0: one monthly-rented RTX PRO 6000 96 GB, EUR 999/month / 730 hours, ECB USD 1.1133/EUR dated 28 Oct 2026, USD 1.5235/hour; average load 70%. Architecture: small gemma, 12B active parameters; throughput 26861.9166667 tokens/s (architecture-class calibration, 29 Oct 2026, efficient-engine prefill; capped at 100,000 tokens/s). The row's own scored cost basis: 726,752 input + 0 output tokens over 1,477 decisions = 492.046039269 tokens/decision. GPU-time cost USD 0.0110741566005038/1,000; old list-price cost USD 0.0246023019634394/1,000; applied min(old list-price cost, GPU-time cost) = USD 0.0110741566005038/1,000. The GPU-time estimate is lower. Estimated, not a bill. Intelligence, Calibration, measured latency and the common cost-item membership are unchanged. Prior prices remain in the archived v1.7 releases.

Measured p50 latency: 0.075 s (on-GPU, no network, loopback; not directly comparable with API latency, which we time end to end from our measuring host, network included)

Ranking and cap use: 0.30 s (est. incl. network (2x + 150 ms))

Self-hosted model: measured p50 0.075 s on-GPU, no network (timed on our GPU over loopback). Not directly comparable with API latency, which we time end to end from our measuring host, network included. The ranking and latency cap use the same estimate for every self-hosted row: 2 × measured + 150 ms = 0.30 s. Model authors can ask us to time a hosted endpoint instead (on request).

x2 + 0.15 s (assumption, not measured)

measured 2026-10-06 on the live v1.6.0 S u P (1,500 rows, 1,477 ok; the 23 refusals are exactly the 23 long-context items, through the author's own "Prompt exceeds context limit; no automatic truncation" guard at their shipped --max-context 16384, although the base model itself declares 262,144 positions). Author's own code unmodified (infer.py / decision.py, sha256 1c5db5de.../43389f44...) with their shipped --backend transformers on the unquantized base and the flags their own EVALUATION.md prescribes FOR JEVBENCH: --prompt-format open-format --effort 1 --temperature 1.0. Their requirements-transformers.txt is missing torchvision, which transformers 5.16.1 needs for the Gemma 4 unified processor; adding it was the only deviation and it changes no numerics. One RTX PRO 6000 Blackwell (Lium, Brasov, Romania), torch 2.12.0+cu130, transformers 5.16.1, peft 0.20.0. Latency axis uses the standard self-hosted x2 + 0.15 s adjustment; raw p50/p95 are in the run 53 receipts; add-requests run 53, benchmarkheaven.com/submit ref 75D5EF0C

Measured latency over 1,500 decisions: p50 0.075 s · p95 0.132 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 & law50.3n=1616
Coding & software50.1n=382
Math & numbers9.8n=370
Finance & commerce45.4n=223
Support & operations42.0n=160
Everyday language61.3n=145
Safety & security56.1n=109

Use cases (TypeSafe categories)

Model routing51.4n=524
Legal & compliance63.5n=515
Customer support44.2n=240
E-commerce38.8n=119
Insurance claims47.9n=119
Risk assessment45.4n=118
Financial crime26.3n=101
Feature extraction27.5n=99
Lead generation53.5n=95
Recruiting12.6n=94
Knowledge graphs46.3n=94
LLM guardrails71.1n=93
Moderation54.6n=93
Code linting53.4n=90
Search & retrieval71.8n=90
Science24.9n=90
Advertising40.7n=88
Gaming0.0n=86
Demand forecasting1.4n=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 68.13 · Composite 63.16 · rank #51 on the all-systems board · #30 open weights

intelligence 48.78 · calibration 87.48 · speed 89.45 · cost 58.27

v1.6 speed basis (124 items): p50 0.073 s · p95 0.116 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