Decider-2B
Quadrant scores
See the full quadrantScored with the public quadrant rubric (maturity × capability; bubble = adoption). Revise as evidence lands.
- Maturity6.4/10
Full train/serve stack, HF cards, and System One API docs put Decider near the top of open maturity; self-host only (no SLA) keeps it under Laya’s packaging lead.
- Capability4.8/10
Official boards (17 Oct): Decision Index 0.3.2 Full 25.8 (#127); JevBench Intelligence 20.7, calibration 68.5, p50 0.015 s.
- Adoption16/100
Visible in the open-Jev / S1Bench wave with a serious repo and HF cards; still niche outside builders already hunting replicas.
Vendor claims
- Live MiniWoB++ click tasks ~93% sampled success on v10 (author; v8 ~83%)[Vendor claim — not independently verified]
- TypeSafe wire format POST /v1/systemone; noul maps to catalog boolean[Vendor claim — not independently verified]
- Also ships Mapika/decider-0.8b sibling with the same supervised recipe[Vendor claim — not independently verified]
News covering this model
Board audit of 17 Oct 2026: see the “Board audit” section below; where it conflicts with older board statements on this page, it wins.
Family update: The newer Decider-4B (v2.1, September 2026) is now #1 on JevBench with 64.13 — the first open model to beat hosted Jev. This 2B variant remains useful for constrained deployments but sits at #34 (30.7).
Decider-2B is an independent open System One–style decision model — full fine-tune of Qwen3.5-2B-Base plus calibration-aware RL (author v10) — not a TypeSafe product and not a LoRA-only adapter.
It reads shared state plus typed questions (choice, score, noul → catalog boolean) and returns calibrated distributions in one forward pass. Wire format targets TypeSafe POST /v1/systemone. Weights: Mapika/decider-2b; code: github.com/Mapika/decider. Smaller sibling: decider-0.8b.
JevBench v1.4.2
| Metric | Decider-2B | Decider-4B | Rank |
|---|---|---|---|
| Overall | 30.7 | 64.13 | #34 / #1 |
| Intelligence | 40.9 | 49.4 | - |
| Calibration | 69.7 | 75.0 | - |
| Speed | 70.9 | 92.9 | - |
| Cost | 64.4 | 60.9 | - |
The 4B variant’s jump to #1 came from speed and cost optimization, not raw intelligence — both share similar training recipes but the larger backbone handles calibration better.
Limits (read before you ship)
- Author benches (browser, games, public JevBench items, Bespoke suite) are self-reported — not ModelSystem.One evals; comps vs Jev / peers are UnverifiedClaim.
- English-centric; knowledge-heavy / multi-hop items stay weak at 2B without splitting reasoning.
- Schema-cache layouts trade some accuracy for speed; fit temperature on your labels.
- Catalog latency band 50–400ms is a placeholder envelope, not a measured SLA.
Why it is in the catalog
Public typed decision I/O, open weights + reproducible train/serve docs, and System One API compatibility. Stronger open full-model peer next to Laya and NanoJev; sits below hosted Jev on adoption.
decider-31b NVFP4 (7 Oct 2026)
Mapika/decider-31b (Apache-2.0) is Gemma-4-31B-it with a fine-tune merged into attention and MLP, quantized to NVFP4 (about 31 GB, FP8 KV cache), served with decider.serve_vllm in decider-ai 1.9.0. Author numbers (UnverifiedClaim): Decision Index 0.3 public suite 64.27 (chance-corrected; raw 73.24, ECE 0.039), run on B300s. That is the public part only, and the entry is not on the official 0.3 board. Scores on this page are unchanged.
Board audit (17 Oct 2026)
Checked against the official boards on 17 Oct 2026: Decision Index 0.3.2 (data of 16 Oct, 19:00 UTC), JevBench and ImageJevBench live. The boards are separate sources and are never averaged. Older board statements and rankings further down this page are superseded where they conflict with this section.
| Board | Row | Result |
|---|---|---|
| Decision Index 0.3.2 (16 Oct 19:00 UTC) | Decider 2B | Full 25.8 (#127, tie group 35); public 29.75 (#127); same-skills 28.47; new-domains 21.04 |
| JevBench open weights (live 17 Oct) | decider-2b | Capability 44.6; Intelligence 20.7; calibration 68.5; p50 0.015 s; $0.015/1k |
| ImageJevBench v0.3.0 | Mapika decider-2b-vision BF16 | Capability 42.8; Intelligence 23.1; calibration 62.6; p50 0.38 s; $0.034/1k |
| ImageJevBench v0.1.5 archive (frozen) | Mapika decider-2b-vision BF16 | Capability 67.1; Intelligence 52.8; calibration 81.5; p50 0.33 s; $0.026/1k |
Version / family note. Related rows on the board: Decider 31B (NVFP4) Full 64.62 (#5), Decider 35B-A3B 48.53 (#64), Decider 4B 40.33 (#94), Decider chat on Gemma-4-31B 57.62 (#33). Only the 2B is scored here; the 31B is a candidate for its own page.
Score update (audit, 17 Oct 2026). Capability 5.2 → 4.8 = types × 0.30 + calibration × 0.25 + latency × 0.25 + accuracy × 0.20 = 4.7 × 0.30 + 7 × 0.25 + 4 × 0.25 + 3 × 0.20 = 4.76 → 4.8. Types, calibration and latency come from the earlier working (4.7 / 7 / 4); only accuracy is re-derived from the board (3; was 5): Decision Index Full 25.8 ÷ 60.11 × 8 = 3.4, half-up. Maturity and adoption unchanged.
Hugging Face on 17 Oct (Mapika/decider-0.8b): 15,914 downloads, 7 likes, licence tag apache-2.0, last modified 2026-09-22.
