Benchmark
Agentset Embedding Recall@10 - DBPedia
Embedding benchmarks measure how well models find related items, for example when matching a search to relevant results. Scores are percentages. Higher is better.
- Models measured
- 15
- Scores recorded
- 15
- Sources
- 1
- IQ weight
- 0.16
Score distribution
- 12%
- Mean
- 12.2%
- Median
- 0.534%
- Std dev
- 10.8%
- 10th percentile
- 12.3%
- 90th percentile
- 10.5%
- Min
This benchmark has a weight of 0.16 for embedding models, measured over 15 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Jina Embeddings v5 Text SmallDBPedia· Agentset | 12.3% |
| 2 | Qwen3 Embedding 8BDBPedia· Agentset | 12.3% |
| 3 | Text Embedding 3 LargeDBPedia· Agentset | 12.3% |
| 4 | Text Embedding 3 SmallDBPedia· Agentset | 12.3% |
| 5 | voyage-3-largeDBPedia· Agentset | 12.3% |
| 6 | BGE M3DBPedia· Agentset | 12.2% |
| 7 | Embed Multilingual V3.0DBPedia· Agentset | 12.2% |
| 8 | voyage-4DBPedia· Agentset | 12.2% |
| 9 | Jina Embeddings v3DBPedia· Agentset | 12.1% |
| 10 | voyage-3.5DBPedia· Agentset | 12.1% |
| 11 | Gemini Embedding 2DBPedia· Agentset | 12% |
| 12 | voyage-3.5-liteDBPedia· Agentset | 12% |
| 13 | Qwen3 Embedding 4BDBPedia· Agentset | 11.9% |
| 14 | Text Embedding 004DBPedia· Agentset | 10.8% |
| 15 | Qwen3 Embedding 0.6BDBPedia· Agentset | 10.5% |