# Closed Visual Question Answering on TM4K Source: [Closed Visual Question Answering on TM4K]() Collection index: [llms.txt]() Data updated: 2026-03-10T08:51:39.325Z Evaluation of model performance on the TM4K dataset for Closed Visual Question Answering, reporting F1, Recall, and Precision. 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 | Closed Visual Question Answering | | Dataset (including any stated split) | TM4K | | Metric | F1 Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 6 of 6 | | 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 - [F1 Score](): Higher is better; unit: PERCENT. - [Recall](): Higher is better; unit: PERCENT. - [Precision](): Higher is better; unit: PERCENT. ## Recorded results | Method | F1 Score | Result date | Report paper | | --- | --- | --- | --- | | EyExIn | 78.07 | Not recorded | 69afa56a2d603e6de3e438df | | Qwen2.5-VL | 55.72 | Not recorded | 69afa56a2d603e6de3e438df | | LLaVA | 39.83 | Not recorded | 69afa56a2d603e6de3e438df | | Gemini3-Pro | 37.99 | Not recorded | 69afa56a2d603e6de3e438df | | ChatGPT-5.2 | 15.93 | Not recorded | 69afa56a2d603e6de3e438df | | Qwen3-VL-Max | 7.82 | Not recorded | 69afa56a2d603e6de3e438df | ### EyExIn F1 Score: 78.07. Result ID: 69afdb966dbb7075b9584fb4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Fine-Tuned"}. This record does not assert independent reproduction. ### Qwen2.5-VL F1 Score: 55.72. Result ID: 69afdb966dbb7075b9584fb3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Fine-Tuned"}. This record does not assert independent reproduction. ### LLaVA F1 Score: 39.83. Result ID: 69afdb966dbb7075b9584fb2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Category":"Fine-Tuned"}. This record does not assert independent reproduction. ### Gemini3-Pro F1 Score: 37.99. Result ID: 69afdb966dbb7075b9584fb1. [Reporting paper]() Recorded evaluation configuration: {"Model Category":"Proprietary"}. This record does not assert independent reproduction. ### ChatGPT-5.2 F1 Score: 15.93. Result ID: 69afdb966dbb7075b9584fb0. [Reporting paper]() Recorded evaluation configuration: {"Model Category":"Proprietary"}. This record does not assert independent reproduction. ### Qwen3-VL-Max F1 Score: 7.82. Result ID: 69afdb966dbb7075b9584faf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Category":"Proprietary"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.