Benchmark
Agentset Embedding Win Rate - business reports
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
- 0.37
Score distribution
- 47.6%
- Mean
- 49.4%
- Median
- 12.8%
- Std dev
- 32.5%
- 10th percentile
- 64.1%
- 90th percentile
- 22.5%
- Min
This benchmark has a weight of 0.37 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 Smallbusiness reports· Agentset | 75% |
| 2 | Gemini Embedding 2business reports· Agentset | 64.1% |
| 3 | voyage-4business reports· Agentset | 58.9% |
| 4 | Text Embedding 3 Largebusiness reports· Agentset | 56.9% |
| 5 | BGE M3business reports· Agentset | 51.2% |
| 6 | Text Embedding 3 Smallbusiness reports· Agentset | 50% |
| 7 | voyage-3.5business reports· Agentset | 50% |
| 8 | Qwen3 Embedding 0.6Bbusiness reports· Agentset | 49.4% |
| 9 | Embed Multilingual V3.0business reports· Agentset | 45.6% |
| 10 | Qwen3 Embedding 4Bbusiness reports· Agentset | 45.6% |
| 11 | voyage-3-largebusiness reports· Agentset | 41.7% |
| 12 | Qwen3 Embedding 8Bbusiness reports· Agentset | 35.6% |
| 13 | voyage-3.5-litebusiness reports· Agentset | 35% |
| 14 | Text Embedding 004business reports· Agentset | 32.5% |
| 15 | Jina Embeddings v3business reports· Agentset | 22.5% |