EN中
← All visual benchmarksMTEB / 2026-10-23
MTEB · RETRIEVAL

Scientific retrieval · SciFact

Retrieval nDCG@10, scaled to points (×100). Selected models, not the official top-10.

Hover or tap a bar to inspect. Select up to 3 models to highlight and compare.
Model scores10 models
Scientific retrieval · SciFact. Zoomed horizontal axis, from 63.66 to 80.24ZOOMED X-AXIS · 63.66 – 80.24 · NOT FROM ZERO63.6667.8071.9576.1080.24Qwen/Qwen3-Embedding-4BQwen/Qwen3-Embedding-4B · 78.33 nDCG@10 × 100 · zoomed horizontal axis78.33Alibaba-NLP/gte-modernbert-baseAlibaba-NLP/gte-modernbert-base · 76.41 nDCG@10 × 100 · zoomed horizontal axis76.41BAAI/bge-large-en-v1.5BAAI/bge-large-en-v1.5 · 74.64 nDCG@10 × 100 · zoomed horizontal axis74.64BAAI/bge-base-en-v1.5BAAI/bge-base-en-v1.5 · 74.34 nDCG@10 × 100 · zoomed horizontal axis74.34mixedbread-ai/mxbai-embed-large-v1mixedbread-ai/mxbai-embed-large-v1 · 73.92 nDCG@10 × 100 · zoomed horizontal axis73.92jinaai/jina-embeddings-v3jinaai/jina-embeddings-v3 · 72.53 nDCG@10 × 100 · zoomed horizontal axis72.53Snowflake/snowflake-arctic-embe…Snowflake/snowflake-arctic-embed-m-v1.5 · 71.84 nDCG@10 × 100 · zoomed horizontal axis71.84BAAI/bge-small-en-v1.5BAAI/bge-small-en-v1.5 · 71.27 nDCG@10 × 100 · zoomed horizontal axis71.27Qwen/Qwen3-Embedding-0.6BQwen/Qwen3-Embedding-0.6B · 69.72 nDCG@10 × 100 · zoomed horizontal axis69.72sentence-transformers/all-mpnet…sentence-transformers/all-mpnet-base-v2 · 65.57 nDCG@10 × 100 · zoomed horizontal axis65.57
Choose a bar for details.

How to read this chart

Selected model sample, not the complete MTEB leaderboard. Results may come from different evaluator versions.

Score unit: nDCG@10 × 100. Values can only be compared within the same task and protocol.

Data retrieved: 2026-10-23. Higher values indicate better results for the reported metric.

Source: MTEB · CC0. Redrawn from released data; reduced to selected models and rounded. Not affiliated with the source organization.

← Explore all benchmark charts