All tasks / Models
bge-reranker-v2-m3
BAAI's small open-weights multilingual cross-encoder reranker built on BGE-M3.
- BAAI
- Open weights
- Released Mar 2024
Where it ranks
- –Embeddings & retrievalModels · Local · no result on this task’s benchmarks yet
Facts
- Vendor
- BAAI
- Family
- BGE Reranker
- Released
- Mar 2024
- Weights
- Open: download and run it yourself
- License
- Apache-2.0
- Parameters
- 0.57B
- GPU memory to run locally
- ~2 GB (Derived: 0.57B parameters x 2 bytes = ~1.1 GB in fp16.)
- Access
- Free (open weights)
- Last verified
- 19 Oct 2026
Benchmark results
| Benchmark | Result | Entry on the leaderboard | As of | Source |
|---|---|---|---|---|
| Agentset Reranker Leaderboard | 1,327 | BAAI/BGE Reranker v2 M3ELO from GPT-5-judged pairwise comparisons; rank 11 of 12; win rate 28.6%; page says 'Last updated: February 15, 2026'. | 15 Feb 2026 | agentset.ai |
Where you can use it
- SvLLMVector databases & engines · Local