TopoGraphRAG-Bench
TopoGraphRAG-Bench: Evaluating Multimodal GraphRAG on Layout-Grounded Evidence Reasoning
AG on Layout-Grounded Evidence Reasoning Ruochi Li · Jianzhe Lin · Haoxuan Zhang · Haihua Chen · Junhua Ding · Edward Gehringer · Yang Zhang 📄 Paper | 🏠 Homepage | 💻 Code | 🔎 Case Study TopoGraphRAG-Bench is a benchmark for layout-grounded multimodal evidence reasoning in GraphRAG.
How to run
$ npm i -g lettokenburn-cli$ ltb bench info topographrag-bench
External harness. No Harbor adapter has been generated for this benchmark yet. `ltb bench info` prints the known links.
Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs
Scores
6 sourced entries| Harness | Source | Confidence | Link | |||
|---|---|---|---|---|---|---|
| RAG-Anything | 54.5 | N/A | Independent | medium | Oct 7, 2026 | arxiv.org |
| MegaRAG | 51.0 | N/A | Independent | medium | Oct 7, 2026 | arxiv.org |
| LightRAG | 46.6 | N/A | Independent | medium | Oct 7, 2026 | arxiv.org |
| Microsoft GraphRAG | 45.9 | N/A | Independent | medium | Oct 7, 2026 | arxiv.org |
| HippoRAG | 44.4 | N/A | Independent | medium | Oct 7, 2026 | arxiv.org |
| VisRAG | 34.1 | N/A | Independent | medium | Oct 7, 2026 | arxiv.org |
Every number links to where it was published. Low-confidence rows are muted and need per-cell verification.
Reproduced by the community
All runsAbout
TopoGraphRAG-Bench: Evaluating Multimodal GraphRAG on Layout-Grounded Evidence Reasoning
Ruochi Li · Jianzhe Lin · Haoxuan Zhang · Haihua Chen · Junhua Ding · Edward Gehringer · Yang Zhang 📄 Paper | 🏠 Homepage | 💻 Code | 🔎 Case Study TopoGraphRAG-Bench is a benchmark for layout-grounded multimodal evidence reasoning in GraphRAG. It contains 2,024 question–answer pairs over 201 long documents sampled from MMDocIR (https://huggingface.co/datasets/MMDocIR/MMDocIR_Eval_Dataset)…