SAVRN Model Hub · Comparisons
bge-reranker-large vs multilingual-e5-large-instruct
Bge-reranker-large has 560M parameters and multilingual-e5-large-instruct has 560M parameters; both are released under MIT License; at 16-bit, bge-reranker-large needs about 1.3 GB (1x MI300X from $1.85 an hour) and multilingual-e5-large-instruct about 1.3 GB (1x MI300X from $1.85 an hour).
| Field | bge-reranker-large BAAI/bge-reranker-large | multilingual-e5-large-instruct intfloat/multilingual-e5-large-instruct |
|---|---|---|
| Publisher | Beijing Academy of Artificial Intelligence | Liang Wang |
| Task | Feature extraction | Feature extraction |
| Modality | Text | Text |
| Parameters, as reported | 560M parameters | 560M parameters |
| Architecture | XLMRobertaForSequenceClassification | XLMRobertaModel |
| Library | transformers | sentence-transformers |
| Context length | 514 tokens | 514 tokens |
| Repository size | 6.7 GB | 3.4 GB |
| Artifact formats | safetensors, onnx, pytorch | safetensors, onnx |
| License | mit | mit |
| Access | Open weights, no gate | Open weights, no gate |
| Memory at 16-bit (weights and margin) | 1.3 GB | 1.3 GB |
| Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Memory at 4-bit (weights and margin) | 0.3 GB | 0.3 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | 55611d7bca2a | 274baa43b0e1 |
| Downloads reported by the hub | 2.2M | 1.6M |
| Last observed | 2026-10-16 | 2026-10-16 |
An evaluation row appears only where at least two of these models report the same benchmark with the same stated configuration, metric, unit and setup. Different evaluators stay named in each cell. Values are shown as reported: no unit conversion, no ranking.
Other Reported Results
These results are listed for each model on its own, because the conditions needed to compare them are not stated or do not match. Two results that leave a condition blank are not assumed to share it.
bge-reranker-large
| Benchmark | Conditions | Result | Reported by | Revision | Date |
|---|---|---|---|---|---|
| MTEB CMedQAv1 | Configuration defaultTask RerankingMetric mapComparison conditions not established | 81.2721 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB CMedQAv1 | Configuration defaultTask RerankingMetric mrrComparison conditions not established | 84.1424 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB CMedQAv2 | Configuration defaultTask RerankingMetric mapComparison conditions not established | 84.1037 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB CMedQAv2 | Configuration defaultTask RerankingMetric mrrComparison conditions not established | 86.7938 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB MMarcoReranking | Configuration defaultTask RerankingMetric mapComparison conditions not established | 35.4601 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB MMarcoReranking | Configuration defaultTask RerankingMetric mrrComparison conditions not established | 34.6024 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB T2Reranking | Configuration defaultTask RerankingMetric mapComparison conditions not established | 67.2773 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB T2Reranking | Configuration defaultTask RerankingMetric mrrComparison conditions not established | 77.1315 | BAAI Publisher reported |
Evaluated revision not stated | — |
multilingual-e5-large-instruct
| Benchmark | Conditions | Result | Reported by | Revision | Date |
|---|---|---|---|---|---|
| MTEB AmazonCounterfactualClassification (de) | Configuration deTask ClassificationMetric accuracyComparison conditions not established | 66.7131 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (de) | Configuration deTask ClassificationMetric apComparison conditions not established | 79.015 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (de) | Configuration deTask ClassificationMetric f1Comparison conditions not established | 64.8195 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (en) | Configuration enTask ClassificationMetric accuracyComparison conditions not established | 76.2388 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (en) | Configuration enTask ClassificationMetric apComparison conditions not established | 39.0735 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (en) | Configuration enTask ClassificationMetric f1Comparison conditions not established | 70.0484 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (en-ext) | Configuration en-extTask ClassificationMetric accuracyComparison conditions not established | 73.8531 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (en-ext) | Configuration en-extTask ClassificationMetric apComparison conditions not established | 22.4475 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (en-ext) | Configuration en-extTask ClassificationMetric f1Comparison conditions not established | 61.0163 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (ja) | Configuration jaTask ClassificationMetric accuracyComparison conditions not established | 76.0493 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (ja) | Configuration jaTask ClassificationMetric apComparison conditions not established | 23.4498 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (ja) | Configuration jaTask ClassificationMetric f1Comparison conditions not established | 62.5723 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonPolarityClassification | Configuration defaultTask ClassificationMetric accuracyComparison conditions not established | 96.2874 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonPolarityClassification | Configuration defaultTask ClassificationMetric apComparison conditions not established | 94.845 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonPolarityClassification | Configuration defaultTask ClassificationMetric f1Comparison conditions not established | 96.2868 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (de) | Configuration deTask ClassificationMetric accuracyComparison conditions not established | 53 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (de) | Configuration deTask ClassificationMetric f1Comparison conditions not established | 52.0083 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (en) | Configuration enTask ClassificationMetric accuracyComparison conditions not established | 56.716 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (en) | Configuration enTask ClassificationMetric f1Comparison conditions not established | 55.7651 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (es) | Configuration esTask ClassificationMetric accuracyComparison conditions not established | 48.806 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (es) | Configuration esTask ClassificationMetric f1Comparison conditions not established | 48.0823 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (fr) | Configuration frTask ClassificationMetric accuracyComparison conditions not established | 48.508 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (fr) | Configuration frTask ClassificationMetric f1Comparison conditions not established | 47.6875 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (ja) | Configuration jaTask ClassificationMetric accuracyComparison conditions not established | 47.71 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (ja) | Configuration jaTask ClassificationMetric f1Comparison conditions not established | 47.0587 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (zh) | Configuration zhTask ClassificationMetric accuracyComparison conditions not established | 44.662 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (zh) | Configuration zhTask ClassificationMetric f1Comparison conditions not established | 43.4237 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_1Comparison conditions not established | 31.721 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_10Comparison conditions not established | 49.221 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_100Comparison conditions not established | 49.884 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_1000Comparison conditions not established | 49.888 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_3Comparison conditions not established | 44.31 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_5Comparison conditions not established | 47.276 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_1Comparison conditions not established | 32.432 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_10Comparison conditions not established | 49.5 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_100Comparison conditions not established | 50.163 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_1000Comparison conditions not established | 50.166 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_3Comparison conditions not established | 44.618 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_5Comparison conditions not established | 47.541 | intfloat Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_1Comparison conditions not established | 31.721 | intfloat Publisher reported |
Evaluated revision not stated | — |
SAVRN's Notes on bge-reranker-large
Nobody gives a reranker its own accelerator, and at 1.3 GB in 16-bit bge-reranker-large shows why. This 560M-parameter XLM-RoBERTa sequence classifier from BAAI ranks retrieved passages for a retrieval-augmented pipeline, so we put it on the same card as that stack. On the cheapest listing the Index shows, a single MI300X with 192 GB at $1.85 an hour on-demand, it occupies under one percent of the memory.
MIT terms apply, so commercial use, modification and redistribution are allowed as long as the copyright and permission notices go with the files. The number to check is 514, the context length in tokens; whatever you hand it per call must fit that window, which sets chunk sizes upstream. The publisher's own page says it released newer rerankers with larger inputs and more languages on 3/18/2024; weigh that against this model's 2024-05-11 last update before standardizing.
SAVRN's Notes on multilingual-e5-large-instruct
Loaded at 16-bit, this encoder needs 1.3 GB of memory for 1.1 GB of weights, a sliver of the 192 GB on the single MI300X our Index lists as the cheapest fit at $1.85 per hour. Nobody rents that card for one 560M-parameter embedding model; it fits beside a serving model on hardware you already run. The output is a 1,024-dimension vector for retrieval, and the publisher initialized it from xlm-roberta-large, so it carries that base's 100 languages.
MIT terms allow commercial use, modification and redistribution provided the copyright and permission notices stay with the files, so building it into a hosted product is simple. Check the 514-token context first: long documents must be chunked before encoding, and that chunking decides recall more than the card does. The Index carries no host prices for it, which fits a model operators run themselves.
Questions
Which is larger, bge-reranker-large or multilingual-e5-large-instruct?
bge-reranker-large (560M parameters) is larger than multilingual-e5-large-instruct (560M parameters), by the parameter counts their publishers report.
Which is cheaper to run, bge-reranker-large or multilingual-e5-large-instruct?
At 4-bit, bge-reranker-large fits on 1x MI300X from $1.85 an hour and multilingual-e5-large-instruct on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use bge-reranker-large commercially?
Yes. bge-reranker-large is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.
Can I use multilingual-e5-large-instruct commercially?
Yes. multilingual-e5-large-instruct is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.