ArguAna

MTEB argument-retrieval benchmark evaluating embedding and retrieval models on finding counterarguments for online debate claims.

14rows
scoreprimary metric
2026-05-06sampled

Metadata

ID
arguana
Category
Retrieval
Release
Unknown

Metrics

nDCG@10

Latest Results

Rows are ranked by the Hugging Face leaderboard API rank. Model display names are preserved from source modelId values.

Rank Subject nDCG@10 Model Match Provenance Sampled
1 google/embeddinggemma-300m 71.53 — Imported 2026-05-06
2 GritLM/GritLM-7B 63.17 — Imported 2026-05-06
3 Snowflake/snowflake-arctic-embed-l-v2.0 59.11 — Imported 2026-05-06
4 ibm-granite/granite-embedding-125m-english 58.40 — Imported 2026-05-06
5 Snowflake/snowflake-arctic-embed-m-v2.0 57.88 — Imported 2026-05-06
6 HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v2 57.42 — Imported 2026-05-06
7 BAAI/bge-m3 54.04 — Imported 2026-05-06
8 nomic-ai/nomic-embed-text-v1.5 52.02 — Imported 2026-05-06
9 sentence-transformers/all-MiniLM-L6-v2 50.17 — Imported 2026-05-06
10 mteb/baseline-bm25s 49.28 — Imported 2026-05-06
11 sentence-transformers/paraphrase-multilingual-mpnet-base-v2 48.91 — Imported 2026-05-06
12 sentence-transformers/all-MiniLM-L12-v2 47.13 — Imported 2026-05-06
13 jinaai/jina-embeddings-v3 43.29 — Imported 2026-05-06
14 sentence-transformers/LaBSE 34.18 — Imported 2026-05-06