Benchmark
MTEB(Code, v1) - Retrieval
Embedding benchmarks measure how well models find related items, for example when matching a search to relevant results. Scores are percentages.
- Models measured
- 13
- Scores recorded
- 13
- Sources
- 1
- IQ weight
- 1.46
Score distribution
- 71.1%
- Mean
- 75.4%
- Median
- 9.6%
- Std dev
- 55.8%
- 10th percentile
- 80.1%
- 90th percentile
- 48.4%
- Min
This benchmark has a weight of 1.46 for embedding models, measured over 13 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 | Qwen3 Embedding 8BRetrieval· MTEB Leaderboard data | 80.7% |
| 2 | Qwen3 Embedding 4BRetrieval· MTEB Leaderboard data | 80.1% |
| 3 | Embed v1 4bRetrieval· MTEB Leaderboard data | 78.7% |
| 4 | embeddinggemma-2Retrieval· MTEB Leaderboard data | 77.9% |
| 5 | Gemini Embedding 001Retrieval· MTEB Leaderboard data | 76% |
| 6 | Embed v1 0.6bRetrieval· MTEB Leaderboard data | 75.9% |
| 7 | Qwen3 Embedding 0.6BRetrieval· MTEB Leaderboard data | 75.4% |
| 8 | Jina Embeddings v5 Text SmallRetrieval· MTEB Leaderboard data | 73.3% |
| 9 | Jina Embeddings v5 Text NanoRetrieval· MTEB Leaderboard data | 71.1% |
| 10 | INF Retriever v1Retrieval· MTEB Leaderboard data | 69.7% |
| 11 | Text Embedding 005Retrieval· MTEB Leaderboard data | 61.5% |
| 12 | Granite Embedding Small English R2Retrieval· MTEB Leaderboard data | 55.8% |
| 13 | Granite Embedding 278m MultilingualRetrieval· MTEB Leaderboard data | 48.4% |