skip to content
gigarouter gigarouter
models / reranker · coming soon

Japanese Reranker Cross-Encoder XSmall V1

hotchpotch/japanese-reranker-cross-encoder-xsmall-v1

published Mar 2024 · updated May 2025

Japanese Reranker Cross-Encoder XSmall V1 is a rerank model that scores the relevance between a query and passages, optimized for Japanese text retrieval.

est. price
~$0.008
/ 1k docs · estimated, set at launch
API providers
0
downloads / mo
55.4K
license
mit

specs

TaskReranking (Cross-Encoder)
Architecture6-layer MiniLMv2 with 384 hidden size
ParametersNot specified
LicenseMIT License

about this model

Model Overview

hotchpotch/japanese-reranker-cross-encoder-xsmall-v1 is a Japanese cross-encoder reranker model that scores the relevance of a query–document pair. It uses 6 transformer layers with a hidden size of 384 and accepts sequences up to 512 tokens.

Benchmark Performance

The model achieves the following scores on four Japanese retrieval evaluation datasets:

DatasetScore
JQaRA0.6136
JaCWIR0.9376
MIRACL0.7411
JSQuAD0.9602

These results place the xsmall variant competitively among Japanese rerankers, outperforming many larger bilingual models while requiring significantly less compute.

Training and Efficiency

The model was trained on six Japanese datasets (JQaRA, JSQuAD, MIRACL, mMARCO, Mr.TyDi, and Wikipedia lead paragraphs) using 15 hard negatives per positive sample. Knowledge distillation from the large variant was applied to improve score quality. On an RTX 3090, evaluating the JaCWIR set took 196 seconds—approximately 6× faster than the large variant—making it suitable for latency-sensitive reranking pipelines.

best for

FAQ

What is the input and output format for this model?

The model takes a query and a list of passages as input, and outputs a relevance score (0 to 1) for each passage.

How does this model compare in speed to the large version?

On an RTX3090, the xsmall variant is about 6x faster than the large variant (196s vs 1253s on JaCWIR evaluation).

What is the license for this model?

The model is released under the MIT License.

How can I call this model via the gigarouter API?

Use the gigarouter OpenAI-compatible endpoint with your API key, sending the query and passages in the request.

not yet live

We're benchmarking and onboarding Japanese Reranker Cross-Encoder XSmall V1 as a hosted, OpenAI-compatible API. Sign in for free credit and be ready when it lands, or tell us you want it and we'll prioritize it.

related reranker models

compare all →