Official benchmarks map / typed-decisions
FINAL-Bench/Darwin-27B-ZTC-v5 is ranked first on the typed-decisions leaderboard with 0.81, 4.7% ahead of FINAL-Bench/Darwin-27B-RSI-Decision. Read live from the Hugging Face API on November 6, 2026.
| # | Model | Organization | Score |
|---|---|---|---|
| 1 | FINAL-Bench/Darwin-27B-ZTC-v5 | FINAL-Bench | 0.81 |
| 2 | FINAL-Bench/Darwin-27B-RSI-Decision | FINAL-Bench | 0.78 |
| 3 | FINAL-Bench/Darwin-27B-ZTC | FINAL-Bench | 0.74 |
| 4 | empiriolabsai/aplomb-1 | empiriolabsai | 0.74 |
| 5 | vllm-sr/d3-turbo | vllm-sr | 0.74 |
| 6 | openjev/openjev | openjev | 0.73 |
| 7 | ProKope-AI/ProKope-421M-8K | ProKope-AI | 0.72 |
| 8 | ProKope-AI/ProKope-421M | ProKope-AI | 0.71 |
| 9 | adaptive-classifier/typed-decisions-minilm-l6-specialist | adaptive-classifier | 0.61 |
typed-decisions is a dataset that Hugging Face marks as an official benchmark. Its leaderboard is built automatically from the .eval_results files that model repositories publish, so entries are mostly self-reported by model authors and evaluation settings differ between submissions. A verified tag appears only where Hugging Face marks an entry as verified.
Original board: huggingface.co/datasets/LocalLLaMA/typed-decisions
Part of the Hugging Face official benchmarks map by QuantID. Unofficial. Not affiliated with or endorsed by Hugging Face.