Primary sourcearXiv cs.AI
View sourceEvent ·Multi-source
APEX-Accounting基准：评估九个前端模型会计能力
Mercor联手Ramp发布APEX-Accounting，内含160个会计任务，覆盖对账、费用计提等真实工作。九个前沿模型参与测试，Claude-Fable-5 (Max)以56.4% Mean Criteria@3领先Muse-Spark-1.1 (xHigh)的52.6%。最高Pass@8仅21.5%（Muse-Spark-1.1），GPT-5.6-Sol (Max+Pro)的Pass^8为2.6%。实验发现辛普森悖论：提高token预算提升总分，但预算受限时高token消耗任务得分更低。
Current read
想看看AI到底能不能做会计？新出的APEX-Accounting基准拿160道真实会计题考了九个模型，最强Claude Fable-5才56%，离实际干活还差得远。
3 sources41° AI heatLast updated 2026/7/29 17:56:49
Evidence
3 sourcesConflict check
Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.