# Event Question Answering on EventMind 1.0 (test) Source: [Event Question Answering on EventMind 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:44:08.733Z Evaluation of Event Question Answering performance on the test split of the EventMind 1.0 dataset, measured using FGQA, HAQA, and MCQA metrics. 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 | Event Question Answering | | Dataset (including any stated split) | EventMind 1.0 (test) | | Metric | FGQA | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 10 of 10 | | 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 - [FGQA](): Higher is better; unit: PERCENT. - [HAQA](): Higher is better; unit: PERCENT. - [MCQA](): Higher is better; unit: PERCENT. ## Recorded results | Method | FGQA | Result date | Report paper | | --- | --- | --- | --- | | EventFlash-7B | 64.2 | Not recorded | 6982d29da8b01e76cc8e9450 | | EventFlash-3B | 61.1 | Not recorded | 6982d29da8b01e76cc8e9450 | | EventFlash-Zero | 60.4 | Not recorded | 6982d29da8b01e76cc8e9450 | | LLaVA-Next-Video | 44.6 | Not recorded | 6982d29da8b01e76cc8e9450 | | Qwen2.5 VL | 43.9 | Not recorded | 6982d29da8b01e76cc8e9450 | | VideoChat2-Flash | 41.9 | Not recorded | 6982d29da8b01e76cc8e9450 | | Qwen2.5 VL | 41.7 | Not recorded | 6982d29da8b01e76cc8e9450 | | InternVL2.5 | 40 | Not recorded | 6982d29da8b01e76cc8e9450 | | VideoChat2-Flash | 38.9 | Not recorded | 6982d29da8b01e76cc8e9450 | | InternVL2.5 | 37 | Not recorded | 6982d29da8b01e76cc8e9450 | ### EventFlash-7B FGQA: 64.2. Result ID: 699750e15698665ec4a29fd2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params":"7B","LLM Backbone":"Qwen-2.5","Max Bins":"1,000"}. This record does not assert independent reproduction. ### EventFlash-3B FGQA: 61.1. Result ID: 699750e15698665ec4a29fd1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params":"3B","LLM Backbone":"Qwen-2.5","Max Bins":"1,000"}. This record does not assert independent reproduction. ### EventFlash-Zero FGQA: 60.4. Result ID: 699750e15698665ec4a29fd0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params":"3B","LLM Backbone":"Qwen-2.5","Max Bins":"1,000"}. This record does not assert independent reproduction. ### LLaVA-Next-Video FGQA: 44.6. Result ID: 699750e15698665ec4a29fcd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Params":"7B","LLM Backbone":"Qwen2.5","Max Bins":"56"}. This record does not assert independent reproduction. ### Qwen2.5 VL FGQA: 43.9. Result ID: 699750e15698665ec4a29fce. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params":"7B","LLM Backbone":"Qwen2.5","Max Bins":"768"}. This record does not assert independent reproduction. ### VideoChat2-Flash FGQA: 41.9. Result ID: 699750e15698665ec4a29fcc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params":"7B","LLM Backbone":"Qwen2.5","Max Bins":"1,000"}. This record does not assert independent reproduction. ### Qwen2.5 VL FGQA: 41.7. Result ID: 699750e15698665ec4a29fc9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params":"3B","LLM Backbone":"Qwen2.5","Max Bins":"768"}. This record does not assert independent reproduction. ### InternVL2.5 FGQA: 40. Result ID: 699750e15698665ec4a29fcf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params":"8B","LLM Backbone":"InternLM2.5"}. This record does not assert independent reproduction. ### VideoChat2-Flash FGQA: 38.9. Result ID: 699750e15698665ec4a29fca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params":"2B","LLM Backbone":"Qwen2.5","Max Bins":"1,000"}. This record does not assert independent reproduction. ### InternVL2.5 FGQA: 37. Result ID: 699750e15698665ec4a29fcb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Params":"4B","LLM Backbone":"Qwen2.5"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.