# Panoramic Visual Question Answering on PanoVQA (test) Source: [Panoramic Visual Question Answering on PanoVQA (test)]() Collection index: [llms.txt]() Data updated: 2026-03-11T09:05:00.859Z Evaluation of model performance on the test split of the PanoVQA dataset for Panoramic Visual Question Answering. 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 | Panoramic Visual Question Answering | | Dataset (including any stated split) | PanoVQA (test) | | Metric | Accuracy (N1) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | 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 (N1)](): Higher is better; unit: PERCENT. - [Accuracy (N2)](): Higher is better; unit: PERCENT. - [Accuracy (N3)](): Higher is better; unit: PERCENT. - [Accuracy (N4)](): Higher is better; unit: PERCENT. - [Accuracy (O1)](): Higher is better; unit: PERCENT. - [Accuracy (O2)](): Higher is better; unit: PERCENT. - [Accuracy (O3)](): Higher is better; unit: PERCENT. - [Accuracy (D1)](): Higher is better; unit: PERCENT. - [Accuracy (D2)](): Higher is better; unit: PERCENT. - [Accuracy (D3)](): Higher is better; unit: PERCENT. - [Accuracy (D4)](): Higher is better; unit: PERCENT. - [Accuracy (D5)](): Higher is better; unit: PERCENT. - [Average Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (N1) | Result date | Report paper | | --- | --- | --- | --- | | PanoLM-7B | 34.79 | Not recorded | 69b0f72f2d603e6de3e45fca | | Qwen2.5-VL-7B | 33.52 | Not recorded | 69b0f72f2d603e6de3e45fca | | Gemini-2.5-Flash-Lite | 18.83 | Not recorded | 69b0f72f2d603e6de3e45fca | | Qwen2.5-VL-32B-Ins. | 16.51 | Not recorded | 69b0f72f2d603e6de3e45fca | | InternVL3-8B-Ins. | 15.06 | Not recorded | 69b0f72f2d603e6de3e45fca | | Qwen2.5-VL-7B-Ins. | 13.65 | Not recorded | 69b0f72f2d603e6de3e45fca | | InternVL2-8B | 12.79 | Not recorded | 69b0f72f2d603e6de3e45fca | | LLaVA-OneVision-7B | 12.54 | Not recorded | 69b0f72f2d603e6de3e45fca | | DeepSeek-VL2-Small | 12.5 | Not recorded | 69b0f72f2d603e6de3e45fca | | GLM-4-9B | 11.73 | Not recorded | 69b0f72f2d603e6de3e45fca | | LLaVA-NEXT-7B | 11.19 | Not recorded | 69b0f72f2d603e6de3e45fca | | Chameleon-7B | 9.87 | Not recorded | 69b0f72f2d603e6de3e45fca | | Grok-3-Mini | 3.38 | Not recorded | 69b0f72f2d603e6de3e45fca | ### PanoLM-7B Accuracy (N1): 34.79. Result ID: 69b130366dbb7075b95bc8f7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Panoramic fine-tuned"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B Accuracy (N1): 33.52. Result ID: 69b130366dbb7075b95bc8f6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Panoramic fine-tuned"}. This record does not assert independent reproduction. ### Gemini-2.5-Flash-Lite Accuracy (N1): 18.83. Result ID: 69b130366dbb7075b95bc8f5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Proprietary"}. This record does not assert independent reproduction. ### Qwen2.5-VL-32B-Ins. Accuracy (N1): 16.51. Result ID: 69b130366dbb7075b95bc8f3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### InternVL3-8B-Ins. Accuracy (N1): 15.06. Result ID: 69b130366dbb7075b95bc8f0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B-Ins. Accuracy (N1): 13.65. Result ID: 69b130366dbb7075b95bc8ee. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### InternVL2-8B Accuracy (N1): 12.79. Result ID: 69b130366dbb7075b95bc8ef. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### LLaVA-OneVision-7B Accuracy (N1): 12.54. Result ID: 69b130366dbb7075b95bc8ed. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### DeepSeek-VL2-Small Accuracy (N1): 12.5. Result ID: 69b130366dbb7075b95bc8f2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### GLM-4-9B Accuracy (N1): 11.73. Result ID: 69b130366dbb7075b95bc8f1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### LLaVA-NEXT-7B Accuracy (N1): 11.19. Result ID: 69b130366dbb7075b95bc8ec. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### Chameleon-7B Accuracy (N1): 9.87. Result ID: 69b130366dbb7075b95bc8eb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### Grok-3-Mini Accuracy (N1): 3.38. Result ID: 69b130366dbb7075b95bc8f4. [Reporting paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Proprietary"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.