Alibaba's gte-Qwen2-7B-instruct has claimed the top position on MTEB with ~70% overall score, excelling in retrieval (nDCG@10) and semantic textual similarity tasks. The 7B parameter model with 3584 dimensions outperforms NVIDIA's NV-Embed-v2 and Voyage AI's voyage-3-large.
92%
Overall ConfidenceBased on 5 weighted dimensions
Confidence Breakdown
Authority
30%95Tier 1
Data Quality
25%100Level 5
Recency
20%808-30 days
Corroboration
15%1003 sources
Specificity
10%100Level 4
Data Points(3)
gte-Qwen2-7B-instruct achieved ~70% overall MTEB score, topping 2000+ models
Dec 28, 2025Open-weight model with 3584 dimensions enables local deployment
Dec 28, 2025
MTEB evaluation spans 56+ datasets across 8 task types for comprehensive assessment
Dec 28, 2025