Benchmark
Agentset Embedding Elo - DBPedia
Embedding benchmarks measure how well models find related items, for example when matching a search to relevant results. Higher scores are better.
- Models measured
- 15
- Scores recorded
- 15
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 1,500
- Mean
- 1,500
- Median
- 0
- Std dev
- 1,500
- 10th percentile
- 1,500
- 90th percentile
- 1,500
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | BGE M3DBPedia· Agentset | 1,500 |
| 2 | Embed Multilingual V3.0DBPedia· Agentset | 1,500 |
| 3 | Gemini Embedding 2DBPedia· Agentset | 1,500 |
| 4 | Jina Embeddings v3DBPedia· Agentset | 1,500 |
| 5 | Jina Embeddings v5 Text SmallDBPedia· Agentset | 1,500 |
| 6 | Qwen3 Embedding 0.6BDBPedia· Agentset | 1,500 |
| 7 | Qwen3 Embedding 4BDBPedia· Agentset | 1,500 |
| 8 | Qwen3 Embedding 8BDBPedia· Agentset | 1,500 |
| 9 | Text Embedding 004DBPedia· Agentset | 1,500 |
| 10 | Text Embedding 3 LargeDBPedia· Agentset | 1,500 |
| 11 | Text Embedding 3 SmallDBPedia· Agentset | 1,500 |
| 12 | voyage-3-largeDBPedia· Agentset | 1,500 |
| 13 | voyage-3.5DBPedia· Agentset | 1,500 |
| 14 | voyage-3.5-liteDBPedia· Agentset | 1,500 |
| 15 | voyage-4DBPedia· Agentset | 1,500 |