Mapika Decider 4B Release - DI 0.3 Sample: leaderboard
Mapika Decider 4B Release - DI 0.3 Sample: Native decision index (0-100). Mapika decider-4b official v3 card: trained Qwen3.5-4B-Base decision model, compared with released older v2.1. Model update is distinct trained weights, not an inference setup. DI 0.3 4500-request sample and JevBench public hard/standard accuracy retained; image-mean old result adds base vision tower, so not presented as the same checkpoint condition. Fresh held-out JevBench-style skill index can be negative: explicit unbounded theoretical scale, not a percentage.
Metric: Native decision index (0-100). Source: huggingface.co. Saturation forecast: Rough model projection: around 2026. 2 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Mapika Decider 4B v3 | 51.02 | |
| 2 | Mapika Decider 4B v2.1 | 41.55 |
Interactive version: theaggregate.ai/benchmark?slug=mapika-decider-4b-release-di-0-3-sample · How It Works · Data refreshed daily, snapshot 2026-11-12.