Notableevaluation benchmarks

SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents

arXiv:2605.21384Papers with Code →

Bingchen Zhao, Dhruv Srikanth, Yuxiang Wu, Zhengyao Jiang

Published
May 20, 2026 — 16:41 UTC
Turing Wire

By Callan Zhang · May 20, 2026 · Editorial standards →

Summarised from the primary source with AI assistance under human editorial oversight. Turing Wire is not a primary source — read the original for the authoritative account.

Source: arXiv cs.AI