JevalKit - DecisionIndex_Vision: leaderboard
JevalKit - DecisionIndex_Vision. Native {"schema_version": 1, "name": "DecisionIndex_Vision", "media_root": "../raw/DecisionIndexVision-0.4.1", "suite_dir": "../raw/DecisionIndexVision-0.4.1", "protocol": "official-public-vision-0.4.1", "records": 12210, "questions": 12210, "sha256": "66c38b3fbbad0877d826d29c8ab4c5177e0afd5c8aab870f75c95a2d5a546920", "family": "DecisionIndex", "modality": "image", "module": "decision_index_vision", "edition": "0.4.1", "source_url": "https://github.com/apolinario/decision-index"}. Complete, input-conformant, eligible primary runs with no runtime failures; text/vision Public Decision Index0-100, all other boards native accuracy fractions converted to percent. Calibration metrics retained separately; private composite components not represented as public. Metric: Public Decision Index (0-100). Higher is better.
Metric: Public Decision Index (0-100). Source: huggingface.co. Saturation forecast: Rough model projection: around 2026. 16 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Valen-Decision-1.5-27B | 82.91 | |
| 2 | Valen-Decision-1.5-9B | 79.93 | |
| 3 | WeMM-JEV | 77.93 | |
| 4 | Valen-Decision-1.5-4B | 77.85 | |
| 5 | Xing-VL2.0-Decision | 77.7 | |
| 6 | vLLM-SR-d3-turbo | 76.84 | |
| 7 | Amos-1-Large | 76.1 | |
| 8 | StartLux-Decision-27B-Instant | 73.83 | |
| 9 | Valen-Decision-1.5-2B | 70.54 | |
| 10 | Valen-4B | 62.52 |
Interactive version: theaggregate.ai/benchmark?slug=jevalkit-decisionindex-vision · How It Works · Data refreshed daily, snapshot 2026-11-13.