# Theory of Mind reasoning on Hi-ToM Source: [Theory of Mind reasoning on Hi-ToM]() Collection index: [llms.txt]() Data updated: 2026-06-11T10:28:21.055Z Evaluation of model performance on Theory of Mind reasoning tasks using the Hi-ToM dataset, reporting accuracy broken down by 0th through 4th order reasoning levels. 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 | Theory of Mind reasoning | | Dataset (including any stated split) | Hi-ToM | | Metric | Accuracy (0th-Order) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 - [Accuracy (0th-Order)](): Higher is better; unit: PERCENT. - [Accuracy (1st-Order)](): Higher is better; unit: PERCENT. - [Accuracy (2nd-Order)](): Higher is better; unit: PERCENT. - [Accuracy (3rd-Order)](): Higher is better; unit: PERCENT. - [Accuracy (4th-Order)](): Higher is better; unit: PERCENT. - [Overall Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (0th-Order) | Result date | Report paper | | --- | --- | --- | --- | | CoT | 100 | Not recorded | 6a2a4138d33dfb23e7839467 | | SIMTOM | 100 | Not recorded | 6a2a4138d33dfb23e7839467 | | TIMETOM | 100 | Not recorded | 6a2a4138d33dfb23e7839467 | | RECTOM | 100 | Not recorded | 6a2a4138d33dfb23e7839467 | | CoT | 100 | Not recorded | 6a2a4138d33dfb23e7839467 | | SIMTOM | 100 | Not recorded | 6a2a4138d33dfb23e7839467 | | TIMETOM | 100 | Not recorded | 6a2a4138d33dfb23e7839467 | | RECTOM | 100 | Not recorded | 6a2a4138d33dfb23e7839467 | | CoT | 100 | Not recorded | 6a2a4138d33dfb23e7839467 | | SIMTOM | 100 | Not recorded | 6a2a4138d33dfb23e7839467 | | TIMETOM | 100 | Not recorded | 6a2a4138d33dfb23e7839467 | | RECTOM | 100 | Not recorded | 6a2a4138d33dfb23e7839467 | | CoT | 100 | Not recorded | 6a2a4138d33dfb23e7839467 | | RECTOM | 100 | Not recorded | 6a2a4138d33dfb23e7839467 | | SIMTOM | 98.75 | Not recorded | 6a2a4138d33dfb23e7839467 | | TIMETOM | 97.5 | Not recorded | 6a2a4138d33dfb23e7839467 | ### CoT Accuracy (0th-Order): 100. Result ID: 6a2a8db3fbc373592c286714. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT-5.4"}. This record does not assert independent reproduction. ### SIMTOM Accuracy (0th-Order): 100. Result ID: 6a2a8db3fbc373592c286715. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT-5.4"}. This record does not assert independent reproduction. ### TIMETOM Accuracy (0th-Order): 100. Result ID: 6a2a8db3fbc373592c286716. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"GPT-5.4"}. This record does not assert independent reproduction. ### RECTOM Accuracy (0th-Order): 100. Result ID: 6a2a8db3fbc373592c286717. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"GPT-5.4"}. This record does not assert independent reproduction. ### CoT Accuracy (0th-Order): 100. Result ID: 6a2a8db3fbc373592c286718. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Gemini-3"}. This record does not assert independent reproduction. ### SIMTOM Accuracy (0th-Order): 100. Result ID: 6a2a8db3fbc373592c286719. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Gemini-3"}. This record does not assert independent reproduction. ### TIMETOM Accuracy (0th-Order): 100. Result ID: 6a2a8db3fbc373592c28671a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Gemini-3"}. This record does not assert independent reproduction. ### RECTOM Accuracy (0th-Order): 100. Result ID: 6a2a8db3fbc373592c28671b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Gemini-3"}. This record does not assert independent reproduction. ### CoT Accuracy (0th-Order): 100. Result ID: 6a2a8db3fbc373592c28671c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3.5"}. This record does not assert independent reproduction. ### SIMTOM Accuracy (0th-Order): 100. Result ID: 6a2a8db3fbc373592c28671d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3.5"}. This record does not assert independent reproduction. ### TIMETOM Accuracy (0th-Order): 100. Result ID: 6a2a8db3fbc373592c28671e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Qwen3.5"}. This record does not assert independent reproduction. ### RECTOM Accuracy (0th-Order): 100. Result ID: 6a2a8db3fbc373592c28671f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Qwen3.5"}. This record does not assert independent reproduction. ### CoT Accuracy (0th-Order): 100. Result ID: 6a2a8db3fbc373592c286720. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Gemma-4"}. This record does not assert independent reproduction. ### RECTOM Accuracy (0th-Order): 100. Result ID: 6a2a8db3fbc373592c286723. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Gemma-4"}. This record does not assert independent reproduction. ### SIMTOM Accuracy (0th-Order): 98.75. Result ID: 6a2a8db3fbc373592c286721. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Gemma-4"}. This record does not assert independent reproduction. ### TIMETOM Accuracy (0th-Order): 97.5. Result ID: 6a2a8db3fbc373592c286722. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Gemma-4"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.