Benchmark
Agentset Embedding nDCG@10 - DBPedia
Embedding benchmarks measure how well models find related items, for example when matching a search to relevant results. Scores are percentages.
- Models measured
- 15
- Scores recorded
- 15
- Sources
- 1
- IQ weight
- 0.62
Score distribution
- 78.5%
- Mean
- 78.9%
- Median
- 2.2%
- Std dev
- 73.7%
- 10th percentile
- 80.7%
- 90th percentile
- 73%
- Min
This benchmark has a weight of 0.62 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 | voyage-4DBPedia· Agentset | 81.1% |
| 2 | Text Embedding 3 SmallDBPedia· Agentset | 80.7% |
| 3 | Jina Embeddings v5 Text SmallDBPedia· Agentset | 80.5% |
| 4 | Qwen3 Embedding 8BDBPedia· Agentset | 79.7% |
| 5 | Text Embedding 3 LargeDBPedia· Agentset | 79.5% |
| 6 | Gemini Embedding 2DBPedia· Agentset | 79.2% |
| 7 | voyage-3-largeDBPedia· Agentset | 79% |
| 8 | Jina Embeddings v3DBPedia· Agentset | 78.9% |
| 9 | Qwen3 Embedding 4BDBPedia· Agentset | 78.7% |
| 10 | voyage-3.5-liteDBPedia· Agentset | 78.7% |
| 11 | BGE M3DBPedia· Agentset | 78.5% |
| 12 | Embed Multilingual V3.0DBPedia· Agentset | 78.3% |
| 13 | voyage-3.5DBPedia· Agentset | 78.2% |
| 14 | Text Embedding 004DBPedia· Agentset | 73.7% |
| 15 | Qwen3 Embedding 0.6BDBPedia· Agentset | 73% |