JevalKit - ZhDecisionBench: leaderboard
JevalKit - ZhDecisionBench. Native {"schema_version": 1, "name": "ZhDecisionBench", "media_root": ".", "protocol": "v0.2-validation-378-native-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": 378, "questions": 467, "sha256": "d99704fc055c8f767813786ce6184089a5ebc8aa4f88a5cc21075108bafbe099", "family": "ZhDecisionBench", "modality": "text", "module": "zh_decision_bench", "source_url": "https://huggingface.co/datasets/CodyQin/zh-decision-bench"}. 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. 34 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Valen-Decision-1.5-4B | 92.72 | |
| 2 | Valen-Decision-1.5-9B | 92.72 | |
| 3 | Intern-Decision 4B | 91.65 | |
| 4 | Valen-Decision-1.5-27B | 91.65 | |
| 5 | Amos-1-Large | 91.43 | |
| 6 | Perplexity Decider v1.1 (Benchmark Sweep Run: source=JevalKit; native=Pplx-Decider%20%28L20Z%29; hardware=L20Z; checkpoint=pplx-decider-v1.1-27b) | 91.43 | |
| 7 | Perplexity Decider v1.1 | 91.22 | |
| 8 | Valen-Decision-1.5-2B | 91.22 | |
| 9 | StartLux-v1.1-9B-Instant | 91.01 | |
| 10 | Clef flash 9.5B | 90.79 |
Interactive version: theaggregate.ai/benchmark?slug=jevalkit-zhdecisionbench · How It Works · Data refreshed daily, snapshot 2026-11-13.