{"task":"Vidore3IndustrialBM25sReranking.v2","id":"reranking-industrial","title":"Reranking · Industry","category":"Rerankers","metric":"nDCG@10 × 100","direction":"higher","precision":3,"publishedAt":null,"interval":null,"observationLabel":null,"datasetRevision":"feb084441e6fc28580a023479211715c28700653","description":"ViDoRe 3 reranking results from MTEB: English queries, the test split, and BM25s first-stage retrieval. Each subject has its own board.","limitations":["These are document retrieval rerankers evaluated on a fixed candidate set, not a general language-model ranking.","Coverage is limited to model revisions with this exact published task and English subset. Missing results are not scored.","The source supplies no confidence interval here; the displayed rank orders point estimates and does not establish statistical significance.","No result publication date is supplied. The retrieval date records when the pinned result files were checked."],"rows":[{"name":"Qwen/Qwen3-VL-Reranker-8B","organization":"Qwen","score":59.489000000000004,"low":null,"high":null,"observations":null,"revision":"407993db318a67dbb333bbeb8b1521fb703a3bb1","evidenceVersion":"2.22.2-2.22.5","rank":1},{"name":"nvidia/Nemotron-3.5-Rerank-8B-BF16","organization":"nvidia","score":59.148999999999994,"low":null,"high":null,"observations":null,"revision":"708e844c3da0bbaa923e9dc310b07da4ffb6a6b5","evidenceVersion":"2.22.5","rank":2},{"name":"KaLM-Embedding/KaLM-Reranker-V1-Large-R2","organization":"KaLM-Embedding","score":56.152,"low":null,"high":null,"observations":null,"revision":"a862dd8581d4cb1b686b5c595c08be405129656c","evidenceVersion":"2.26.30","rank":3},{"name":"Qwen/Qwen3-VL-Reranker-2B","organization":"Qwen","score":55.92700000000001,"low":null,"high":null,"observations":null,"revision":"4bd860ac4f15ad1897a214615cccc700f8f71818","evidenceVersion":"2.24.9","rank":4},{"name":"nvidia/llama-nemotron-rerank-vl-1b-v2","organization":"nvidia","score":55.541,"low":null,"high":null,"observations":null,"revision":"b8a9987b05b75db5ad949c825cbcbf6eb7c48b5a","evidenceVersion":"2.22.2-2.22.5","rank":5},{"name":"KaLM-Embedding/KaLM-Reranker-V1-Small-R2","organization":"KaLM-Embedding","score":55.208999999999996,"low":null,"high":null,"observations":null,"revision":"68b74f09ff2ab5df9b9a9a48c812a81aaff8815e","evidenceVersion":"2.26.30","rank":6},{"name":"KaLM-Embedding/KaLM-Reranker-V1-Nano-R2","organization":"KaLM-Embedding","score":53.291999999999994,"low":null,"high":null,"observations":null,"revision":"32b242bb7fd7ad6fd404154c09560d249ffe017f","evidenceVersion":"2.26.30","rank":7},{"name":"BAAI/bge-reranker-v2-m3","organization":"BAAI","score":49.373,"low":null,"high":null,"observations":null,"revision":"953dc6f6f85a1b2dbfca4c34a2796e7dde08d41e","evidenceVersion":"2.24.7","rank":8}],"source":{"id":"rerankers","publisher":"MTEB / embeddings-benchmark","href":"https://github.com/embeddings-benchmark/results","licence":"CC0-1.0","licenceUrl":"https://github.com/embeddings-benchmark/results/blob/aee638c23eabc3300a1212087d1ea031a2280e76/LICENSE","revision":"aee638c23eabc3300a1212087d1ea031a2280e76","fetchedAt":"2026-11-05T06:35:30.674Z","evidence":[{"file":"067a6bdc988c1d557ca7213fc8d070cdf426514ef7cb1f907c6888186b9bf437.json","sha256":"067a6bdc988c1d557ca7213fc8d070cdf426514ef7cb1f907c6888186b9bf437","url":"https://api.github.com/repos/embeddings-benchmark/results/commits/main","revision":null,"role":"metadata"},{"file":"a2010f343487d3f7618affe54f789f5487602331c0a8d03f49e9a7c547cf0499.txt","sha256":"a2010f343487d3f7618affe54f789f5487602331c0a8d03f49e9a7c547cf0499","url":"https://raw.githubusercontent.com/embeddings-benchmark/results/aee638c23eabc3300a1212087d1ea031a2280e76/LICENSE","revision":"aee638c23eabc3300a1212087d1ea031a2280e76","role":"licence"},{"file":"85b6e198dbde04d66a991ae919fef7d35ff29b4cad8ddaefaa6a04136ef64ae3.json","sha256":"85b6e198dbde04d66a991ae919fef7d35ff29b4cad8ddaefaa6a04136ef64ae3","url":"https://raw.githubusercontent.com/embeddings-benchmark/results/aee638c23eabc3300a1212087d1ea031a2280e76/results/BAAI__bge-reranker-v2-m3/953dc6f6f85a1b2dbfca4c34a2796e7dde08d41e/model_meta.json","revision":"aee638c23eabc3300a1212087d1ea031a2280e76","role":"model"},{"file":"3f7db2edaf4e4a032d82cfd408cd3ed7dc4b3a04766a7507892e9cb3df43263a.json","sha256":"3f7db2edaf4e4a032d82cfd408cd3ed7dc4b3a04766a7507892e9cb3df43263a","url":"https://raw.githubusercontent.com/embeddings-benchmark/results/aee638c23eabc3300a1212087d1ea031a2280e76/results/BAAI__bge-reranker-v2-m3/953dc6f6f85a1b2dbfca4c34a2796e7dde08d41e/Vidore3IndustrialBM25sReranking.v2.json","revision":"aee638c23eabc3300a1212087d1ea031a2280e76","role":"result"},{"file":"3de913c2af6645bd25ff629b2880555d4e470eb91d549b14caa091b1b8a9ae88.json","sha256":"3de913c2af6645bd25ff629b2880555d4e470eb91d549b14caa091b1b8a9ae88","url":"https://raw.githubusercontent.com/embeddings-benchmark/results/aee638c23eabc3300a1212087d1ea031a2280e76/results/KaLM-Embedding__KaLM-Reranker-V1-Large-R2/a862dd8581d4cb1b686b5c595c08be405129656c/model_meta.json","revision":"aee638c23eabc3300a1212087d1ea031a2280e76","role":"model"},{"file":"fc21d310ebd18b6e47eadaee2b1fcec795fe100c35758252b12380d85e37b43e.json","sha256":"fc21d310ebd18b6e47eadaee2b1fcec795fe100c35758252b12380d85e37b43e","url":"https://raw.githubusercontent.com/embeddings-benchmark/results/aee638c23eabc3300a1212087d1ea031a2280e76/results/KaLM-Embedding__KaLM-Reranker-V1-Large-R2/a862dd8581d4cb1b686b5c595c08be405129656c/Vidore3IndustrialBM25sReranking.v2.json","revision":"aee638c23eabc3300a1212087d1ea031a2280e76","role":"result"},{"file":"93dfadb32f8f15055bfdba3d7b23da2bdb535e762e0ec167c7bc47c8fc8aa3dc.json","sha256":"93dfadb32f8f15055bfdba3d7b23da2bdb535e762e0ec167c7bc47c8fc8aa3dc","url":"https://raw.githubusercontent.com/embeddings-benchmark/results/aee638c23eabc3300a1212087d1ea031a2280e76/results/KaLM-Embedding__KaLM-Reranker-V1-Nano-R2/32b242bb7fd7ad6fd404154c09560d249ffe017f/model_meta.json","revision":"aee638c23eabc3300a1212087d1ea031a2280e76","role":"model"},{"file":"0ccc2208ca67d63d17b5bdb1a6d922725a308346fcd165e4553f25f6492e05fe.json","sha256":"0ccc2208ca67d63d17b5bdb1a6d922725a308346fcd165e4553f25f6492e05fe","url":"https://raw.githubusercontent.com/embeddings-benchmark/results/aee638c23eabc3300a1212087d1ea031a2280e76/results/KaLM-Embedding__KaLM-Reranker-V1-Nano-R2/32b242bb7fd7ad6fd404154c09560d249ffe017f/Vidore3IndustrialBM25sReranking.v2.json","revision":"aee638c23eabc3300a1212087d1ea031a2280e76","role":"result"},{"file":"25ef04976191e38617daf6c211c002e65070e2342d92d1abbac452bc4be3f6ed.json","sha256":"25ef04976191e38617daf6c211c002e65070e2342d92d1abbac452bc4be3f6ed","url":"https://raw.githubusercontent.com/embeddings-benchmark/results/aee638c23eabc3300a1212087d1ea031a2280e76/results/KaLM-Embedding__KaLM-Reranker-V1-Small-R2/68b74f09ff2ab5df9b9a9a48c812a81aaff8815e/model_meta.json","revision":"aee638c23eabc3300a1212087d1ea031a2280e76","role":"model"},{"file":"774ab2d2e4b1274df621c793fe73a1d1fe9fa15ce9a8e17c9b9a55c73136ac78.json","sha256":"774ab2d2e4b1274df621c793fe73a1d1fe9fa15ce9a8e17c9b9a55c73136ac78","url":"https://raw.githubusercontent.com/embeddings-benchmark/results/aee638c23eabc3300a1212087d1ea031a2280e76/results/KaLM-Embedding__KaLM-Reranker-V1-Small-R2/68b74f09ff2ab5df9b9a9a48c812a81aaff8815e/Vidore3IndustrialBM25sReranking.v2.json","revision":"aee638c23eabc3300a1212087d1ea031a2280e76","role":"result"},{"file":"f1f3b963b2bb8c1a8d12bb6b8b506eee5abfecefd8c3b712b307e377c167a3a7.json","sha256":"f1f3b963b2bb8c1a8d12bb6b8b506eee5abfecefd8c3b712b307e377c167a3a7","url":"https://raw.githubusercontent.com/embeddings-benchmark/results/aee638c23eabc3300a1212087d1ea031a2280e76/results/Qwen__Qwen3-VL-Reranker-2B/4bd860ac4f15ad1897a214615cccc700f8f71818/model_meta.json","revision":"aee638c23eabc3300a1212087d1ea031a2280e76","role":"model"},{"file":"e588ee92fda4d95c90b1b495cd36622678c97648d6308784be4df52fc1d6d326.json","sha256":"e588ee92fda4d95c90b1b495cd36622678c97648d6308784be4df52fc1d6d326","url":"https://raw.githubusercontent.com/embeddings-benchmark/results/aee638c23eabc3300a1212087d1ea031a2280e76/results/Qwen__Qwen3-VL-Reranker-2B/4bd860ac4f15ad1897a214615cccc700f8f71818/Vidore3IndustrialBM25sReranking.v2.json","revision":"aee638c23eabc3300a1212087d1ea031a2280e76","role":"result"},{"file":"145589768b2b1eb97f9e04e7cd3257742402842fc8b2e77e9473393e9e543cd2.json","sha256":"145589768b2b1eb97f9e04e7cd3257742402842fc8b2e77e9473393e9e543cd2","url":"https://raw.githubusercontent.com/embeddings-benchmark/results/aee638c23eabc3300a1212087d1ea031a2280e76/results/Qwen__Qwen3-VL-Reranker-8B/407993db318a67dbb333bbeb8b1521fb703a3bb1/model_meta.json","revision":"aee638c23eabc3300a1212087d1ea031a2280e76","role":"model"},{"file":"a531b6b20f405a6e676652d8a0752fcccc0ca542ed327c6f77f05632036e4cd8.json","sha256":"a531b6b20f405a6e676652d8a0752fcccc0ca542ed327c6f77f05632036e4cd8","url":"https://raw.githubusercontent.com/embeddings-benchmark/results/aee638c23eabc3300a1212087d1ea031a2280e76/results/Qwen__Qwen3-VL-Reranker-8B/407993db318a67dbb333bbeb8b1521fb703a3bb1/Vidore3IndustrialBM25sReranking.v2.json","revision":"aee638c23eabc3300a1212087d1ea031a2280e76","role":"result"},{"file":"0e19b8c1a685ff712c71a798a251919e56c5285ab45b944520fc14b165d4bd2e.json","sha256":"0e19b8c1a685ff712c71a798a251919e56c5285ab45b944520fc14b165d4bd2e","url":"https://raw.githubusercontent.com/embeddings-benchmark/results/aee638c23eabc3300a1212087d1ea031a2280e76/results/nvidia__Nemotron-3.5-Rerank-8B-BF16/708e844c3da0bbaa923e9dc310b07da4ffb6a6b5/model_meta.json","revision":"aee638c23eabc3300a1212087d1ea031a2280e76","role":"model"},{"file":"057e9a626f3f991b6b88608b168dddc512c085d82667f17e8990abf1c46cfe3b.json","sha256":"057e9a626f3f991b6b88608b168dddc512c085d82667f17e8990abf1c46cfe3b","url":"https://raw.githubusercontent.com/embeddings-benchmark/results/aee638c23eabc3300a1212087d1ea031a2280e76/results/nvidia__Nemotron-3.5-Rerank-8B-BF16/708e844c3da0bbaa923e9dc310b07da4ffb6a6b5/Vidore3IndustrialBM25sReranking.v2.json","revision":"aee638c23eabc3300a1212087d1ea031a2280e76","role":"result"},{"file":"09e36039fe33ed0e700c432ebea1f9aef49bb2ef96d266ad7ac80b4a7a9124ad.json","sha256":"09e36039fe33ed0e700c432ebea1f9aef49bb2ef96d266ad7ac80b4a7a9124ad","url":"https://raw.githubusercontent.com/embeddings-benchmark/results/aee638c23eabc3300a1212087d1ea031a2280e76/results/nvidia__llama-nemotron-rerank-vl-1b-v2/b8a9987b05b75db5ad949c825cbcbf6eb7c48b5a/model_meta.json","revision":"aee638c23eabc3300a1212087d1ea031a2280e76","role":"model"},{"file":"ba3989398b09b8d19f74d678af5334b3fb714acd1258609329ee3dc3a8bbcdf2.json","sha256":"ba3989398b09b8d19f74d678af5334b3fb714acd1258609329ee3dc3a8bbcdf2","url":"https://raw.githubusercontent.com/embeddings-benchmark/results/aee638c23eabc3300a1212087d1ea031a2280e76/results/nvidia__llama-nemotron-rerank-vl-1b-v2/b8a9987b05b75db5ad949c825cbcbf6eb7c48b5a/Vidore3IndustrialBM25sReranking.v2.json","revision":"aee638c23eabc3300a1212087d1ea031a2280e76","role":"result"}]},"status":"fresh"}