LlamaIndex
We track 4 benchmarks that LlamaIndex made or helped make.
0 in use 3 with public code 4 with a leaderboard here
Benchmarks
| Name | Kind | Released | Best score | Status |
|---|---|---|---|---|
| ParseBench Document parsers process about 2,000 human-verified enterprise pages. Over 169,000 test rules score tables, charts, content faithfulness, formatting and visual grounding. | Documents, charts and text in images | Apr 2026 | 78.8% | Not in cards |
| ExtractBench Systems read a full business document and return a schema-valid JSON object with every requested value. Unified value F1 compares the output with the expected values. | Documents, charts and text in images | Jul 2026 | 95.3% | Not in cards |
| ParseBench-2 Parsers extract text, formatting, tables, charts, layout, and forms from 4,317 page cases across 2,645 documents. Rule checks score six dimensions and average them equally. | Documents, charts and text in images | Nov 2026 | 87% | Not in cards |
| ExtractBench Pro Systems extract every schema value from long-tail synthetic documents with charts, drawn relations, house rules and jargon. Scored by value F1 and by grounded F1, which also needs the source location. | Documents, charts and text in images | Oct 2026 | 58% | Not in cards |