List your company

Free-form Visual Question Answering on camroll

6.33Judge ScoreOracle
-0.25321.45593.1654.8741Jun 3, 2026

Evaluation results

MethodLinks
OracleBase Model=Gemini-2.5-Flash, Retrieval Embedding=no retrieval step, Build Time=0.0h, Build Tokens=~2.0k2026.066.33100
All imagesBase Model=Gemini-2.5-Flash, Retrieval Embedding=no retrieval step, Build Time=0.0h, Build Tokens=~750k2026.065.01100
camroll-agentBase Model=Gemini-2.5-Flash, Retrieval Embedding=all-MiniLM-L6-v2, Build Time=1.5h, Build Tokens=~3.2k2026.064.1183.1
All captionsBase Model=Gemini-2.5-Flash, Retrieval Embedding=no retrieval step, Build Time=1.5h, Build Tokens=~150k2026.063.82100
ClaudeCodeBase Model=Sonnet-4.6, Retrieval Embedding=proprietary, unclear trace, Build Time=0.0h, Build Tokens=~59.0k2026.063.77—
Mem0Base Model=Gemini-2.5-Flash, Retrieval Embedding=text-embedding-small-3, Build Time=1.5h, Build Tokens=~1.0k2026.062.6875.3
HippoRAG2Base Model=Gemini-2.5-Flash, Retrieval Embedding=NV-Embed-v2, Build Time=1.6h, Build Tokens=~1.0k2026.062.5850.1
LightMemBase Model=Gemini-2.5-Flash, Retrieval Embedding=all-MiniLM-L6-v2, Build Time=1.5h, Build Tokens=~1.0k2026.062.4470.2
Self-RAGBase Model=LLama-2, Retrieval Embedding=contriever-msmarco, Build Time=1.5h, Build Tokens=~2.0k2026.062.4119.8
SimpleMemBase Model=Gemini-2.5-Flash, Retrieval Embedding=Qwen3-Embedding-0.6B, Build Time=3.0h, Build Tokens=~0.5k2026.061.758.6
MemOSBase Model=Gemini-2.5-Flash, Retrieval Embedding=BAAI/bge-m3, Build Time=4.0h, Build Tokens=~3.1k2026.061.0927.3
NothingBase Model=Gemini-2.5-Flash, Retrieval Embedding=no retrieval step, Build Time=0.0h, Build Tokens=~502026.0600