# Multi-choice Visual Question Answering on camroll Source: [Multi-choice Visual Question Answering on camroll]() Collection index: [llms.txt]() Data updated: 2026-06-05T07:45:47.276Z Evaluation of model performance on the camroll dataset specifically for the Multi-choice Visual Question Answering task. 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 | Multi-choice Visual Question Answering | | Dataset (including any stated split) | camroll | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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](): Higher is better; unit: PERCENT. - [Recall](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Oracle | 86.4 | Not recorded | 6a22584f86173ad9c1468888 | | All images | 76.5 | Not recorded | 6a22584f86173ad9c1468888 | | camroll-agent | 70.5 | Not recorded | 6a22584f86173ad9c1468888 | | All captions | 63.4 | Not recorded | 6a22584f86173ad9c1468888 | | ClaudeCode | 54 | Not recorded | 6a22584f86173ad9c1468888 | | Mem0 | 53.2 | Not recorded | 6a22584f86173ad9c1468888 | | LightMem | 52.7 | Not recorded | 6a22584f86173ad9c1468888 | | HippoRAG2 | 48.5 | Not recorded | 6a22584f86173ad9c1468888 | | Self-RAG | 46.2 | Not recorded | 6a22584f86173ad9c1468888 | | SimpleMem | 44.6 | Not recorded | 6a22584f86173ad9c1468888 | | MemOS | 32.3 | Not recorded | 6a22584f86173ad9c1468888 | | Nothing | 30 | Not recorded | 6a22584f86173ad9c1468888 | ### Oracle Accuracy: 86.4. Result ID: 6a227e8ffbc373592c20327d. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Gemini-2.5-Flash","Retrieval Embedding":"no retrieval step","Build Time":"0.0h","Build Tokens":"~2.0k"}. This record does not assert independent reproduction. ### All images Accuracy: 76.5. Result ID: 6a227e8ffbc373592c20327c. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Gemini-2.5-Flash","Retrieval Embedding":"no retrieval step","Build Time":"0.0h","Build Tokens":"~750k"}. This record does not assert independent reproduction. ### camroll-agent Accuracy: 70.5. Result ID: 6a227e8ffbc373592c203285. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"Gemini-2.5-Flash","Retrieval Embedding":"all-MiniLM-L6-v2","Build Time":"1.5h","Build Tokens":"~3.2k"}. This record does not assert independent reproduction. ### All captions Accuracy: 63.4. Result ID: 6a227e8ffbc373592c20327b. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Gemini-2.5-Flash","Retrieval Embedding":"no retrieval step","Build Time":"1.5h","Build Tokens":"~150k"}. This record does not assert independent reproduction. ### ClaudeCode Accuracy: 54. Result ID: 6a227e8ffbc373592c203284. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Sonnet-4.6","Retrieval Embedding":"proprietary, unclear trace","Build Time":"0.0h","Build Tokens":"~59.0k"}. This record does not assert independent reproduction. ### Mem0 Accuracy: 53.2. Result ID: 6a227e8ffbc373592c203282. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Gemini-2.5-Flash","Retrieval Embedding":"text-embedding-small-3","Build Time":"1.5h","Build Tokens":"~1.0k"}. This record does not assert independent reproduction. ### LightMem Accuracy: 52.7. Result ID: 6a227e8ffbc373592c203281. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Gemini-2.5-Flash","Retrieval Embedding":"all-MiniLM-L6-v2","Build Time":"1.5h","Build Tokens":"~1.0k"}. This record does not assert independent reproduction. ### HippoRAG2 Accuracy: 48.5. Result ID: 6a227e8ffbc373592c20327f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Gemini-2.5-Flash","Retrieval Embedding":"NV-Embed-v2","Build Time":"1.6h","Build Tokens":"~1.0k"}. This record does not assert independent reproduction. ### Self-RAG Accuracy: 46.2. Result ID: 6a227e8ffbc373592c20327e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"LLama-2","Retrieval Embedding":"contriever-msmarco","Build Time":"1.5h","Build Tokens":"~2.0k"}. This record does not assert independent reproduction. ### SimpleMem Accuracy: 44.6. Result ID: 6a227e8ffbc373592c203280. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"Gemini-2.5-Flash","Retrieval Embedding":"Qwen3-Embedding-0.6B","Build Time":"3.0h","Build Tokens":"~0.5k"}. This record does not assert independent reproduction. ### MemOS Accuracy: 32.3. Result ID: 6a227e8ffbc373592c203283. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Gemini-2.5-Flash","Retrieval Embedding":"BAAI/bge-m3","Build Time":"4.0h","Build Tokens":"~3.1k"}. This record does not assert independent reproduction. ### Nothing Accuracy: 30. Result ID: 6a227e8ffbc373592c20327a. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Gemini-2.5-Flash","Retrieval Embedding":"no retrieval step","Build Time":"0.0h","Build Tokens":"~50"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.