Benchmark
MTEB(Code, v1) - Mean (TaskType)
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 8BMean (TaskType)· MTEB Leaderboard data | 80.7% |
| 2 | Qwen3 Embedding 4BMean (TaskType)· MTEB Leaderboard data | 80.1% |
| 3 | Embed v1 4bMean (TaskType)· MTEB Leaderboard data | 78.7% |
| 4 | embeddinggemma-2Mean (TaskType)· MTEB Leaderboard data | 77.9% |
| 5 | Gemini Embedding 001Mean (TaskType)· MTEB Leaderboard data | 76% |
| 6 | Embed v1 0.6bMean (TaskType)· MTEB Leaderboard data | 75.9% |
| 7 | Qwen3 Embedding 0.6BMean (TaskType)· MTEB Leaderboard data | 75.4% |
| 8 | Jina Embeddings v5 Text SmallMean (TaskType)· MTEB Leaderboard data | 73.3% |
| 9 | Jina Embeddings v5 Text NanoMean (TaskType)· MTEB Leaderboard data | 71.1% |
| 10 | INF Retriever v1Mean (TaskType)· MTEB Leaderboard data | 69.7% |
| 11 | Text Embedding 005Mean (TaskType)· MTEB Leaderboard data | 61.5% |
| 12 | Granite Embedding Small English R2Mean (TaskType)· MTEB Leaderboard data | 55.8% |
| 13 | Granite Embedding 278m MultilingualMean (TaskType)· MTEB Leaderboard data | 48.4% |