Benchmark
Agents Last Exam
An evaluation benchmark for agents whose name echoes Humanity's Last Exam, assessing agents' practical ability to complete professional, multi-step tasks, covering cross-application operations, information retrieval and integration, and long-horizon planning.
Timeline (last 90 days)
Oct 28
According to data published by OpenAI, on the Agents Last Exam benchmark, at medium reasoning effort, GPT-6.1 Terra scored 57.6% and GPT-5.6 Terra scored 42.6%, an improvement of 15 percentage points.
Unverified50%