BAAI/BGE Reranker v2 M3 vs Contextual AI Rerank v2 Instruct

Detailed comparison between BAAI/BGE Reranker v2 M3 and Contextual AI Rerank v2 Instruct. See which reranker best meets your accuracy and performance needs.

Model Comparison

Contextual AI Rerank v2 Instruct takes the lead.

Both BAAI/BGE Reranker v2 M3 and Contextual AI Rerank v2 Instruct are powerful reranking models designed to improve retrieval quality in RAG applications. However, their performance characteristics differ in important ways.

Why Contextual AI Rerank v2 Instruct:

  • Contextual AI Rerank v2 Instruct has 82 higher ELO rating
  • BAAI/BGE Reranker v2 M3 is 1120ms faster on average
  • Contextual AI Rerank v2 Instruct has a 12.2% higher win rate

Overview

Key metrics

ELO Rating

Overall ranking quality

BAAI/BGE Reranker v2 M3

1468

Contextual AI Rerank v2 Instruct

1550

Win Rate

Head-to-head performance

BAAI/BGE Reranker v2 M3

33.0%

Contextual AI Rerank v2 Instruct

45.2%

Accuracy (nDCG@10)

Ranking quality metric

BAAI/BGE Reranker v2 M3

0.686

Contextual AI Rerank v2 Instruct

0.687

Average Latency

Response time

BAAI/BGE Reranker v2 M3

1891ms

Contextual AI Rerank v2 Instruct

3010ms

Visual Performance Analysis

Performance

ELO Rating Comparison

Win/Loss/Tie Breakdown

Accuracy Across Datasets (nDCG@10)

Latency Distribution (ms)

Breakdown

How the models stack up

MetricBAAI/BGE Reranker v2 M3Contextual AI Rerank v2 InstructDescription
Overall Performance
ELO Rating
1468
1550
Overall ranking quality based on pairwise comparisons
Win Rate
33.0%
45.2%
Percentage of comparisons won against other models
Pricing & Availability
Price per 1M tokens
$0.020
$0.050
Cost per million tokens processed
Release Date
2023-09-15
2025-09-12
Model release date
Accuracy Metrics
Avg nDCG@10
0.686
0.687
Normalized discounted cumulative gain at position 10
Performance Metrics
Avg Latency
1891ms
3010ms
Average response time across all datasets

Dataset Performance

By field

Comprehensive comparison of accuracy metrics (nDCG, Recall) and latency percentiles for each benchmark dataset.

FiQa

MetricBAAI/BGE Reranker v2 M3Contextual AI Rerank v2 InstructDescription
Accuracy Metrics
nDCG@5
0.112
0.119
Ranking quality at top 5 results
nDCG@10
0.120
0.125
Ranking quality at top 10 results
Recall@5
0.105
0.123
% of relevant docs in top 5
Recall@10
0.130
0.135
% of relevant docs in top 10
Latency Metrics
Mean
1309ms
2913ms
Average response time
P50
1316ms
2863ms
50th percentile (median)
P90
1744ms
3289ms
90th percentile

PG

MetricBAAI/BGE Reranker v2 M3Contextual AI Rerank v2 InstructDescription
Accuracy Metrics
Latency Metrics
Mean
2457ms
3195ms
Average response time
P50
1019ms
2951ms
50th percentile (median)
P90
1469ms
3781ms
90th percentile

business reports

MetricBAAI/BGE Reranker v2 M3Contextual AI Rerank v2 InstructDescription
Accuracy Metrics
Latency Metrics
Mean
1143ms
2883ms
Average response time
P50
1106ms
2686ms
50th percentile (median)
P90
1641ms
3161ms
90th percentile

MSMARCO

MetricBAAI/BGE Reranker v2 M3Contextual AI Rerank v2 InstructDescription
Accuracy Metrics
nDCG@5
0.985
0.975
Ranking quality at top 5 results
nDCG@10
0.985
0.975
Ranking quality at top 10 results
Recall@5
1.000
1.000
% of relevant docs in top 5
Recall@10
1.000
1.000
% of relevant docs in top 10
Latency Metrics
Mean
2176ms
2952ms
Average response time
P50
812ms
2853ms
50th percentile (median)
P90
980ms
3398ms
90th percentile

DBPedia

MetricBAAI/BGE Reranker v2 M3Contextual AI Rerank v2 InstructDescription
Accuracy Metrics
nDCG@5
0.715
0.734
Ranking quality at top 5 results
nDCG@10
0.778
0.772
Ranking quality at top 10 results
Recall@5
0.063
0.067
% of relevant docs in top 5
Recall@10
0.106
0.108
% of relevant docs in top 10
Latency Metrics
Mean
1332ms
2803ms
Average response time
P50
831ms
2786ms
50th percentile (median)
P90
1455ms
3138ms
90th percentile

Explore More

Compare more rerankers

See how all reranking models stack up. Compare Cohere, Jina AI, Voyage, ZeRank, and more. View comprehensive benchmarks, compare performance metrics, and find the perfect reranker for your RAG application.