Skip to content

Darwin-27B-ZTC

FINAL_BenchDecision modelOpen weights

Darwin-27B-ZTC by FINAL_Bench is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text. It scores 62.5 on the Jev Decision Index (rank 4).

Pricing

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

Specifications

Provider
FINAL_Bench
Parameters
26B
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
FINAL-Bench/Darwin-27B-RSI
Jev-compatible request
Yes
Runs on CPU
No
License
apache-2.0
Hugging Face
FINAL-Bench/Darwin-27B-ZTC

Benchmarks

Jev Decision IndexECE 0.045
62.5

Jev Decision Index: public 62.6, ECE 0.045, Brier 0.333. 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.

Typed Decisions (agreement with teacher)Self-reportedTyped Decisions test accuracy (zero-shot), HF eval-results submission (unverified)
0.743
Jev Decision Index public suite (self-run)Self-reportedDecision Index public balanced skill, edition 0.3 kit (release-v3), self-run
62.6

Speed & latency

Median latency per call (Decision Index)
104 ms

Compare Darwin-27B-ZTC with…

FAQ

How much does Darwin-27B-ZTC cost?

Darwin-27B-ZTC has no hosted price listed; its weights are open, so the cost is the compute you run it on.

What questions can Darwin-27B-ZTC answer?

Darwin-27B-ZTC answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.

Is Darwin-27B-ZTC well calibrated?

On the Jev Decision Index its expected calibration error (ECE) is 0.045; below about 0.05, a stated 80% confidence is right roughly 80% of the time.

Is Darwin-27B-ZTC open weight, and can it run on a CPU?

Yes, Darwin-27B-ZTC 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, Hugging Face). Pricing is per 1M tokens (USD); confirm with the provider before production use.