RAG Question Answering on HotpotQA
47.67F1 ScoreFirecrawl Extract
Evaluation Results
| Method | Links | |
|---|---|---|
| Firecrawl Extractanswer model=Gemma3-27B-it, Avg. Tokens=13192025.12 | 47.67 | |
| IndexLM-0.6Banswer model=Gemma3-27B-it, Avg. Tokens=19662025.12 | 47.63 | |
| IndexLM-4Banswer model=Gemma3-27B-it, Avg. Tokens=19282025.12 | 46.83 | |
| IndexLM-1.7Banswer model=Gemma3-27B-it, Avg. Tokens=20432025.12 | 45.87 | |
| Firecrawl Extractanswer model=Qwen3-4B, Avg. Tokens=13192025.12 | 45.42 | |
| Qwen3-4B + promptanswer model=Gemma3-27B-it, Avg. Tokens=25632025.12 | 43.68 | |
| IndexLM-4Banswer model=Qwen3-4B, Avg. Tokens=19282025.12 | 41.56 | |
| IndexLM-1.7Banswer model=Qwen3-4B, Avg. Tokens=20432025.12 | 41.43 | |
| HtmlRAGanswer model=Gemma3-27B-it, Avg. Tokens=35622025.12 | 40.87 | |
| IndexLM-0.6Banswer model=Qwen3-4B, Avg. Tokens=19662025.12 | 40.37 | |
| Qwen3-4B + promptanswer model=Qwen3-4B, Avg. Tokens=25632025.12 | 39.23 | |
| Chunk-Rerankanswer model=Gemma3-27B-it, Avg. Tokens=40942025.12 | 38.39 | |
| Markdown (raw)answer model=Gemma3-27B-it, Avg. Tokens=40962025.12 | 36.21 | |
| Chunk-Rerankanswer model=Qwen3-4B, Avg. Tokens=40942025.12 | 33.96 | |
| HtmlRAGanswer model=Qwen3-4B, Avg. Tokens=35622025.12 | 32.82 | |
| ReaderLM-v2answer model=Gemma3-27B-it, Avg. Tokens=40002025.12 | 30.59 | |
| Markdown (raw)answer model=Qwen3-4B, Avg. Tokens=40962025.12 | 29.82 | |
| ReaderLM-v2answer model=Qwen3-4B, Avg. Tokens=40002025.12 | 26.99 | |
| HTML (raw)answer model=Gemma3-27B-it, Avg. Tokens=40962025.12 | 22.01 | |
| HTML (raw)answer model=Qwen3-4B, Avg. Tokens=40962025.12 | 19.22 |