JevalKit - VisualDecisionBench_Image: leaderboard
JevalKit - VisualDecisionBench_Image. Native {"schema_version": 1, "name": "VisualDecisionBench_Image", "media_root": "../media/VisualDecisionBench", "protocol": "native-shared-state", "records": 1402, "questions": 2000, "sha256": "4db5a36bb084f5143d537a107e1685a2d01a3cbd7bf7c8717dd414d91e9aa67a", "family": "VisualDecisionBench", "modality": "image", "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. 32 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Valen-Decision-1.5-27B | 89.94 | |
| 2 | Valen-Decision-1.5-9B | 89.71 | |
| 3 | WeMM-JEV | 87.12 | |
| 4 | Perplexity Decider v1.1 (Benchmark Sweep Run: source=JevalKit; native=Pplx-Decider%20%28L20Z%29; hardware=L20Z; checkpoint=pplx-decider-v1.1-27b) | 86.94 | |
| 5 | Perplexity Decider v1.1 | 86.88 | |
| 6 | Valen-Decision-1.5-4B | 86.76 | |
| 7 | Amos-1-Large | 86.71 | |
| 8 | StartLux-Decision-27B-Instant | 86.53 | |
| 9 | Xing-VL2.0-Decision | 86.06 | |
| 10 | vLLM-SR-d3-turbo | 85.35 |
Interactive version: theaggregate.ai/benchmark?slug=jevalkit-visualdecisionbench-image · How It Works · Data refreshed daily, snapshot 2026-11-13.