JevalKit - VisualDecisionBench_Video: leaderboard
JevalKit - VisualDecisionBench_Video. Native {"schema_version": 1, "name": "VisualDecisionBench_Video", "media_root": "../media/VisualDecisionBench", "protocol": "native-shared-state", "records": 294, "questions": 7143, "sha256": "72a0d2421a439212fa749a320df5d90570d87ad37570561a5dd06d3d5f3be7ed", "family": "VisualDecisionBench", "modality": "video", "module": "visual_decision_bench", "source_url": "https://huggingface.co/datasets/Valen-Team/VisualDecisionBench"}. 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: Accuracy (%). Higher is better.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Rough model projection: around 2026. 10 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Valen-Decision-1.5-27B | 89.4 | |
| 2 | Clef flash 9.5B | 87.81 | |
| 3 | Valen-Decision-1.5-9B | 87.58 | |
| 4 | Valen-4B | 87.43 | |
| 5 | Valen-Decision-1.5-4B | 87.19 | |
| 6 | Valen-2B | 82.74 | |
| 7 | Valen-Decision-1.5-2B | 82.56 | |
| 8 | Valen-0.8B | 79.01 | |
| 9 | Valen-Decision-1.5-0.8B | 74.72 | |
| 10 | OmniJev | 63.36 |
Interactive version: theaggregate.ai/benchmark?slug=jevalkit-visualdecisionbench-video · How It Works · Data refreshed daily, snapshot 2026-11-13.