---
title: answerdotai/answerai-colbert-small-v1 (Encode)
description: answerai-colbert-small-v1 is a new, proof-of-concept model by Answer.AI, showing the strong performance multi-vector models with the new JaC. BERT, 33M parameters.
canonical_url: https://superlinked.com/models/answerdotai-answerai-colbert-small-v1--encode
last_updated: 2026-05-25
---

# answerdotai/answerai-colbert-small-v1 (Encode)

answerai-colbert-small-v1 is a new, proof-of-concept model by Answer.AI, showing the strong performance multi-vector models with the new JaColBERTv2.5 training recipe and some extra tweaks can reach, even with just 33 million parameters.

Source: [answerdotai/answerai-colbert-small-v1 on HuggingFace](https://huggingface.co/answerdotai/answerai-colbert-small-v1)

## Overview

| Field | Value |
|-------|-------|
| Architecture | BERT |
| Parameters | 33M |
| Tasks | Encode, Score |
| Outputs | Multi-Vec |
| Dimensions | Multi-Vec: 96 |
| Max sequence length | 512 tokens |
| License | apache-2.0 |
| Inputs | text |
| Languages | en |

## Benchmarks

### CQADupstackPhysicsRetrieval

Domain: scientific · Task: retrieval · Language: en

Duplicate question retrieval from StackExchange Physics

Corpus: 38,314 · Queries: 1,039

**Quality:** ndcg at 10: 0.4154 · map at 10: 0.3645 · mrr at 10: 0.4213

**Performance (L4 b1 c16):** Corpus 44.9K tok/s · Corpus p50 45.2ms · Query 4.5K tok/s · Query p50 37.7ms

[Reference](http://nlp.cis.unimelb.edu.au/resources/cqadupstack/)

### CosQA

Domain: technology · Task: retrieval · Language: en

Code search with natural language queries

Corpus: 6,267 · Queries: 500

**Quality:** ndcg at 10: 0.2844 · map at 10: 0.2180 · mrr at 10: 0.2069

**Performance (L4 b1 c16):** Corpus 19.0K tok/s · Corpus p50 43.5ms · Query 2.3K tok/s · Query p50 40.6ms

[Reference](https://arxiv.org/abs/2105.13239)

### FiQA2018

Domain: finance · Task: retrieval · Language: en

Financial opinion mining and question answering

Corpus: 57,599 · Queries: 648

**Quality:** ndcg at 10: 0.4103 · map at 10: 0.3338 · mrr at 10: 0.4965

**Performance (L4 b1 c16):** Corpus 49.3K tok/s · Corpus p50 47.9ms · Query 4.5K tok/s · Query p50 40.0ms

[Reference](https://sites.google.com/view/fiqa/)

### LegalBenchConsumerContractsQA

Domain: legal · Task: retrieval · Language: en

Question answering on consumer contracts

Corpus: 153 · Queries: 396

**Quality:** ndcg at 10: 0.7840 · map at 10: 0.7315 · mrr at 10: 0.7315

**Performance (L4 b1 c16):** Corpus 115.6K tok/s · Corpus p50 62.7ms · Query 6.4K tok/s · Query p50 40.8ms

[Reference](https://huggingface.co/datasets/nguha/legalbench)

### NFCorpus

Domain: medical · Task: retrieval · Language: en

Biomedical literature search from NutritionFacts.org

Corpus: 3,593 · Queries: 323

**Quality:** ndcg at 10: 0.3715 · map at 10: 0.1440 · mrr at 10: 0.5870

**Performance (L4 b1 c16):** Corpus 75.8K tok/s · Corpus p50 55.4ms · Query 1.9K tok/s · Query p50 41.4ms

[Reference](https://www.cl.uni-heidelberg.de/statnlpgroup/nfcorpus/)

### NanoFiQA2018Retrieval

Domain: finance · Task: retrieval · Language: en

Smaller subset of the FiQA financial QA dataset

**Quality:** ndcg at 10: 0.5563 · map at 10: 0.4718 · mrr at 10: 0.6192

**Performance (L4 b1 c16):** Corpus 43.6K tok/s · Corpus p50 44.3ms · Query 4.0K tok/s · Query p50 35.0ms

[Reference](https://sites.google.com/view/fiqa/)

### SCIDOCS

Domain: scientific · Task: retrieval · Language: en

Citation prediction, document classification, and recommendation for scientific papers

Corpus: 25,656 · Queries: 1,000

**Quality:** ndcg at 10: 0.1778 · map at 10: 0.1046 · mrr at 10: 0.3078

**Performance (L4 b1 c16):** Corpus 59.1K tok/s · Corpus p50 47.2ms · Query 4.7K tok/s · Query p50 38.2ms

[Reference](https://allenai.org/data/scidocs)

### SciFact

Domain: scientific · Task: retrieval · Language: en

Scientific claim verification using research literature

Corpus: 5,183 · Queries: 300

**Quality:** ndcg at 10: 0.7405 · map at 10: 0.7015 · mrr at 10: 0.7120

**Performance (L4 b1 c16):** Corpus 75.3K tok/s · Corpus p50 51.0ms · Query 6.7K tok/s · Query p50 39.6ms

[Reference](https://github.com/allenai/scifact)

### StackOverflowQA

Domain: technology · Task: retrieval · Language: en

Programming question answering from Stack Overflow

Corpus: 19,931 · Queries: 1,994

**Quality:** ndcg at 10: 0.5461 · map at 10: 0.5130 · mrr at 10: 0.5130

**Performance (L4 b1 c16):** Corpus 62.1K tok/s · Corpus p50 53.0ms · Query 88.2K tok/s · Query p50 52.4ms

[Reference](https://arxiv.org/abs/2407.02883)