# Multi-domain Knowledge and Reasoning on HLE (official) Source: [Multi-domain Knowledge and Reasoning on HLE (official)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:42:28.116Z Evaluation of model performance on the official version of the Humanity’s Last Exam (HLE) dataset, focusing on Multi-domain Knowledge and Reasoning capabilities, measured by Exact Match percentage. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Multi-domain Knowledge and Reasoning | | Dataset (including any stated split) | HLE (Humanity’s Last Exam) (official) | | Metric | Exact Match | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 7 of 7 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Exact Match](): Higher is better; unit: PERCENT. ## Recorded results | Method | Exact Match | Result date | Report paper | | --- | --- | --- | --- | | GPT-5 pro | 42 | Not recorded | 69818138a8b01e76cc8e238f | | ChatGPT Agent | 41.6 | Not recorded | 69818138a8b01e76cc8e238f | | Tendem’s AI agent | 39 | Not recorded | 69818138a8b01e76cc8e238f | | GPT-5 high | 35.2 | Not recorded | 69818138a8b01e76cc8e238f | | ChatGPT Deep Research | 26.6 | Not recorded | 69818138a8b01e76cc8e238f | | o3 high | 24.3 | Not recorded | 69818138a8b01e76cc8e238f | | Perplexity Deep Research | 21.1 | Not recorded | 69818138a8b01e76cc8e238f | ### GPT-5 pro Exact Match: 42. Result ID: 699658345698665ec49d8ccd. [Reporting paper]() Recorded evaluation configuration: {"tools":"with tools"}. This record does not assert independent reproduction. ### ChatGPT Agent Exact Match: 41.6. Result ID: 699658345698665ec49d8ccb. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Tendem’s AI agent Exact Match: 39. Result ID: 699658345698665ec49d8cca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"human involvement":"none"}. This record does not assert independent reproduction. ### GPT-5 high Exact Match: 35.2. Result ID: 699658345698665ec49d8cce. [Reporting paper]() Recorded evaluation configuration: {"tools":"with tools"}. This record does not assert independent reproduction. ### ChatGPT Deep Research Exact Match: 26.6. Result ID: 699658345698665ec49d8ccc. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### o3 high Exact Match: 24.3. Result ID: 699658345698665ec49d8ccf. [Reporting paper]() Recorded evaluation configuration: {"tools":"with tools"}. This record does not assert independent reproduction. ### Perplexity Deep Research Exact Match: 21.1. Result ID: 699658345698665ec49d8cd0. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.