# Spatial Reasoning QA on SAT-Real Source: [Spatial Reasoning QA on SAT-Real]() Collection index: [llms.txt]() Data updated: 2026-05-13T08:03:46.424Z Evaluation of Spatial Reasoning Question Answering performance on the SAT-Real dataset, reporting average accuracy and specific sub-metrics including Entity Match (EM), Object Match (OM), Action (EA), Goal Aim (GA), and Perspective (Pers). 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 | Spatial Reasoning QA | | Dataset (including any stated split) | SAT-Real | | Metric | Average Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 4 of 4 | | 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 - [Average Accuracy](): Higher is better; unit: PERCENT. - [Entity Match (EM)](): Higher is better; unit: PERCENT. - [Object Match (OM)](): Higher is better; unit: PERCENT. - [Entity Action (EA)](): Higher is better; unit: PERCENT. - [Goal Aim (GA)](): Higher is better; unit: PERCENT. - [Perspective (Pers)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Average Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Gemini-3.0 + 3D Belief | 88.7 | Not recorded | 6a0405b6dbc836b87d827683 | | Gemini-3.0 + SWM | 86.7 | Not recorded | 6a0405b6dbc836b87d827683 | | Gemini-3.0 + SVC | 86 | Not recorded | 6a0405b6dbc836b87d827683 | | Gemini-3.0 | 85.3 | Not recorded | 6a0405b6dbc836b87d827683 | ### Gemini-3.0 + 3D Belief Average Accuracy: 88.7. Result ID: 6a042ffd47f34ce924e9eb2e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Models":"Gemini-3.0 + 3D Belief"}. This record does not assert independent reproduction. ### Gemini-3.0 + SWM Average Accuracy: 86.7. Result ID: 6a042ffd47f34ce924e9eb2c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Models":"Gemini-3.0 + SWM"}. This record does not assert independent reproduction. ### Gemini-3.0 + SVC Average Accuracy: 86. Result ID: 6a042ffd47f34ce924e9eb2d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Models":"Gemini-3.0 + SVC"}. This record does not assert independent reproduction. ### Gemini-3.0 Average Accuracy: 85.3. Result ID: 6a042ffd47f34ce924e9eb2b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Models":"Gemini-3.0"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.