decides.io // open source · coming soon

One model, not two.

It talks, and it decides from the same memory.

Open source · coming soon talks · thinks · decides see the numbers ↓ see the numbers ↓ see the numbers ↓
// in plain numbers

Same size. Smarter decisions.

We put decides next to other AI models of the same size on the Decision Index, a public test of 38 everyday decision tasks. Every score is out of 100: higher is better.

Large models (about 27B)

B = billions: a rough measure of an AI’s size
  • The same base AI, without our upgrade55.7
  • Best other AI of this size57.4
  • The leaderboard’s #1 (any size)57.9
  • decides, instant60.8
  • decides, thinks when unsure67.1
050100

Mid-size models (9B to 12B)

our smaller version
  • Best other AI of this size50.0
  • decides 9B, instant55.5estimate

Where it gets much better

Before: the same AI answering in one go. After: with our upgrades.

Hardest logic puzzles
24%→70%
checks and fixes its work
Medium logic puzzles
27%→82%
checks and fixes its work
Hard science questions
29→69
thinks when unsure
Spotting phishing emails
26→70
thinks when unsure
A tough public decision test (JevBench, hard set)
73%→91%
thinks when unsure
Reading science diagrams
79→86
its built-in decision skill
Quick
Answers in about 0.17 seconds when it’s sure, and tells you how sure it is.
Careful
Stops to think only when it isn’t sure, so hard questions get the attention they need.
Self-checking
Checks its own answer against the rules and fixes what’s wrong.

Scores are out of 100. Ours are our own runs, not yet submitted to the leaderboard. Other models’ scores were measured by the leaderboard (Decision Index, September 2026). The 9B score is an estimate from a large sample of the test. Built on open models: Qwen3.8-27B and Cloudflare’s Clef, both Apache-2.0.

Download the infographic (PNG) · PDF