- dataset: id: LocalLLaMA/typed-decisions task_id: accuracy value: 0.7525 date: "2026-10-31" source: url: https://huggingface.co/datasets/LocalLLaMA/typed-decisions/discussions/58 name: "Typed Decisions official zero-shot leaderboard (PR #58, bench/score_with_jobs.py)" - dataset: id: LocalLLaMA/typed-decisions task_id: kl_from_gold value: 0.1508 date: "2026-10-31" source: url: https://huggingface.co/datasets/LocalLLaMA/typed-decisions/discussions/58 name: "Typed Decisions official zero-shot leaderboard (PR #58, bench/score_with_jobs.py)" - dataset: id: LocalLLaMA/typed-decisions task_id: brier value: 0.0795 date: "2026-10-31" source: url: https://huggingface.co/datasets/LocalLLaMA/typed-decisions/discussions/58 name: "Typed Decisions official zero-shot leaderboard (PR #58, bench/score_with_jobs.py)" - dataset: id: LocalLLaMA/typed-decisions task_id: ece value: 0.0947 date: "2026-10-31" source: url: https://huggingface.co/datasets/LocalLLaMA/typed-decisions/discussions/58 name: "Typed Decisions official zero-shot leaderboard (PR #58, bench/score_with_jobs.py)"