Benchmark
MTEB(cmn, 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
- 7
- Scores recorded
- 7
- Sources
- 1
- IQ weight
- 1.24
Score distribution
- 65.6%
- Mean
- 64.2%
- Median
- 6.2%
- Std dev
- 60.5%
- 10th percentile
- 73.5%
- 90th percentile
- 57.9%
- Min
This benchmark has a weight of 1.24 for embedding models, measured over 7 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 | 75% |
| 2 | Qwen3 Embedding 4BMean (TaskType)· MTEB Leaderboard data | 73.5% |
| 3 | Qwen3 Embedding 0.6BMean (TaskType)· MTEB Leaderboard data | 67.5% |
| 4 | Jina Embeddings v5 Text SmallMean (TaskType)· MTEB Leaderboard data | 64.2% |
| 5 | Multilingual E5 Large InstructMean (TaskType)· MTEB Leaderboard data | 60.7% |
| 6 | E5 Mistral 7B InstructMean (TaskType)· MTEB Leaderboard data | 60.5% |
| 7 | Multilingual E5 LargeMean (TaskType)· MTEB Leaderboard data | 57.9% |