Cohere Rerank 4 Fast vs Cohere Rerank 4 Pro

Detailed comparison between Cohere Rerank 4 Fast and Cohere Rerank 4 Pro. See which reranker best meets your accuracy and performance needs.

Model Comparison

Cohere Rerank 4 Pro takes the lead.

Both Cohere Rerank 4 Fast and Cohere Rerank 4 Pro are powerful reranking models designed to improve retrieval quality in RAG applications. However, their performance characteristics differ in important ways.

Why Cohere Rerank 4 Pro:

  • Cohere Rerank 4 Pro has 120 higher ELO rating
  • Cohere Rerank 4 Pro has a 8.9% higher win rate

Overview

Key metrics

ELO Rating

Overall ranking quality

Cohere Rerank 4 Fast

1506

Cohere Rerank 4 Pro

1627

Win Rate

Head-to-head performance

Cohere Rerank 4 Fast

49.3%

Cohere Rerank 4 Pro

58.2%

Accuracy (nDCG@10)

Ranking quality metric

Cohere Rerank 4 Fast

N/A

Cohere Rerank 4 Pro

N/A

Average Latency

Response time

Cohere Rerank 4 Fast

447ms

Cohere Rerank 4 Pro

614ms

Visual Performance Analysis

Performance

ELO Rating Comparison

Win/Loss/Tie Breakdown

Latency Distribution (ms)

Breakdown

How the models stack up

MetricCohere Rerank 4 FastCohere Rerank 4 ProDescription
Overall Performance
ELO Rating
1506
1627
Overall ranking quality based on pairwise comparisons
Win Rate
49.3%
58.2%
Percentage of comparisons won against other models
Pricing & Availability
Price per 1M tokens
$0.050
$0.050
Cost per million tokens processed
Release Date
2025-12-11
2025-12-11
Model release date
Accuracy Metrics
Avg nDCG@10
N/A
N/A
Normalized discounted cumulative gain at position 10
Performance Metrics
Avg Latency
447ms
614ms
Average response time across all datasets

Dataset Performance

By field

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

MSMARCO

MetricCohere Rerank 4 FastCohere Rerank 4 ProDescription
Latency Metrics
Mean
403ms
458ms
Average response time
P50
382ms
408ms
50th percentile (median)
P90
486ms
615ms
90th percentile

arguana

MetricCohere Rerank 4 FastCohere Rerank 4 ProDescription
Latency Metrics
Mean
574ms
785ms
Average response time
P50
562ms
768ms
50th percentile (median)
P90
728ms
933ms
90th percentile

FiQa

MetricCohere Rerank 4 FastCohere Rerank 4 ProDescription
Latency Metrics
Mean
485ms
610ms
Average response time
P50
459ms
585ms
50th percentile (median)
P90
624ms
817ms
90th percentile

business reports

MetricCohere Rerank 4 FastCohere Rerank 4 ProDescription
Latency Metrics
Mean
428ms
529ms
Average response time
P50
408ms
498ms
50th percentile (median)
P90
550ms
675ms
90th percentile

PG

MetricCohere Rerank 4 FastCohere Rerank 4 ProDescription
Latency Metrics
Mean
492ms
760ms
Average response time
P50
439ms
720ms
50th percentile (median)
P90
650ms
896ms
90th percentile

DBPedia

MetricCohere Rerank 4 FastCohere Rerank 4 ProDescription
Latency Metrics
Mean
297ms
541ms
Average response time
P50
297ms
489ms
50th percentile (median)
P90
309ms
729ms
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.