Standard One 8B SH (v3)

Standard ThinkingDecision modelOpen weights

Standard One 8B SH (v3) by Standard Thinking is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text. It scores 45.0 on the Jev Decision Index (rank 64).

Pricing

No hosted price is listed. The weights are open: the cost is your own compute.

Specifications

Provider: Standard Thinking
Parameters: 9B
Released: Oct 2026
Open weights: Yes
Question types: Choice (one of N options), Score (ordered rubric), Yes / no
Mechanism: Decoder LM with a decision readout
Backbone: StandardThinking/StandardOne-8B
Jev-compatible request: Yes
Runs on CPU: No
License: apache-2.0
Hugging Face: StandardThinking/StandardOne-8B-SH

Benchmarks

Jev Decision IndexECE 0.080: 45.0
Benchmark Heaven JevBench (Capability): 60.0

Jev Decision Index: public 48.3, ECE 0.080, Brier 0.420. Lower ECE means its probabilities can be taken at face value.

Self-reported by the publisher

The model's own claims, often on its own sets or a self-run copy of a public suite. Not independently verified and never ranked alongside measured results.

Jev Decision Index public suite (self-run)Self-reportedDecision Index public balanced skill, edition 0.3 kit (release-v3), self-run: 57.4

Speed & latency

Median latency per call (Decision Index)

80 ms

Compare Standard One 8B SH (v3) with…

Standard One 8B SH (v3) vs amos-1-large—/1M in Standard One 8B SH (v3) vs amos-1-medium—/1M in Standard One 8B SH (v3) vs Celeris-1 Decision$0.04/1M in Standard One 8B SH (v3) vs ScaleDown Classify-1$0.04/1M in Standard One 8B SH (v3) vs Cloudflare clef—/1M in Standard One 8B SH (v3) vs Cloudflare clef-flash—/1M in

FAQ

How much does Standard One 8B SH (v3) cost?

Standard One 8B SH (v3) has no hosted price listed; its weights are open, so the cost is the compute you run it on.

What questions can Standard One 8B SH (v3) answer?

Standard One 8B SH (v3) answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.

Is Standard One 8B SH (v3) well calibrated?

On the Jev Decision Index its expected calibration error (ECE) is 0.080; below about 0.05, a stated 80% confidence is right roughly 80% of the time.

Is Standard One 8B SH (v3) open weight, and can it run on a CPU?

Yes, Standard One 8B SH (v3) has open weights. It needs a GPU to run at useful speed.

Data as of 2026-10-14. Source: Metatext decision-model catalogue, 2026-10-14 (Jev Decision Index, Benchmark Heaven JevBench, Hugging Face). Pricing is per 1M tokens (USD); confirm with the provider before production use.