JevalKit - TypedDecisions: leaderboard
JevalKit - TypedDecisions. Native {"schema_version": 1, "name": "TypedDecisions", "media_root": ".", "protocol": "test-400-shared-state-soft-gold-v1", "reference_normalization": "sum-normalized only within 0.001 of one; original sum retained", "tie_break": "first upstream candidate; explicit mapping retained per question", "records": 400, "questions": 2000, "sha256": "043b3089dac5ab2045e717d3899afe7bfc073e30e66da3cb47b8ebca17277cfe", "family": "TypedDecisions", "modality": "text", "module": "typed_decisions", "source_url": "https://huggingface.co/datasets/LocalLLaMA/typed-decisions"}. 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. 33 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | StartLux-v1.1-9B-Instant | 81.35 | |
| 2 | StartLux-Decision-27B-Instant | 81.1 | |
| 3 | Intern-Decision 4B | 80.5 | |
| 4 | Valen-Decision-1.5-27B | 79.4 | |
| 5 | Intern-Decision 2B | 79.35 | |
| 6 | StartLux-v1.1-4B-Instant | 78.8 | |
| 7 | RSI-Jev-v4 | 78.4 | |
| 8 | StartLux-v1.1-2B-Instant | 78.05 | |
| 9 | Valen-Decision-1.5-9B | 77.8 | |
| 10 | Intern-Decision 0.8B | 77.7 |
Interactive version: theaggregate.ai/benchmark?slug=jevalkit-typeddecisions · How It Works · Data refreshed daily, snapshot 2026-11-13.