Benchmark
Agentset Embedding Elo - FiQa
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 M3FiQa· Agentset | 1,500 |
| 2 | Embed Multilingual V3.0FiQa· Agentset | 1,500 |
| 3 | Gemini Embedding 2FiQa· Agentset | 1,500 |
| 4 | Jina Embeddings v3FiQa· Agentset | 1,500 |
| 5 | Jina Embeddings v5 Text SmallFiQa· Agentset | 1,500 |
| 6 | Qwen3 Embedding 0.6BFiQa· Agentset | 1,500 |
| 7 | Qwen3 Embedding 4BFiQa· Agentset | 1,500 |
| 8 | Qwen3 Embedding 8BFiQa· Agentset | 1,500 |
| 9 | Text Embedding 004FiQa· Agentset | 1,500 |
| 10 | Text Embedding 3 LargeFiQa· Agentset | 1,500 |
| 11 | Text Embedding 3 SmallFiQa· Agentset | 1,500 |
| 12 | voyage-3-largeFiQa· Agentset | 1,500 |
| 13 | voyage-3.5FiQa· Agentset | 1,500 |
| 14 | voyage-3.5-liteFiQa· Agentset | 1,500 |
| 15 | voyage-4FiQa· Agentset | 1,500 |