jev-mahjong-bench
hamakyo/jev-mahjong-bench
Reproducible riichi mahjong benchmark for Jev, GPT, Mortal, and hybrid agents using MJAI and RiichiEnv.
- 星标
- 1
- 派生
- 0
收录依据
README 报告作者对 Jev 与 GPT 在相同立直麻将局面下作选择的比较;本次未复现其结果。
hamakyo/jev-mahjong-bench
Reproducible riichi mahjong benchmark for Jev, GPT, Mortal, and hybrid agents using MJAI and RiichiEnv.
README 报告作者对 Jev 与 GPT 在相同立直麻将局面下作选择的比较;本次未复现其结果。
A learning scaffold for TypeSafe AI's System One models: eval harness plus a measured, plain-language comparison of the Jev decision model vs an LLM stand-in on 24 real operational decisions. All numbers reproducible from committed run files.
共同主题: benchmark, evaluation
Three measured experiments on RAG hallucination: quote-checking, TypeSafe's Jev, and IBM's STAIR. 850+ graded questions, raw responses included.
共同主题: benchmark, evaluation
First independent head-to-head benchmark of System One decision models (Laya vs Jev) on byte-identical inputs
共同主题: benchmark, evaluation