Contextual AI Rerank v2 Instruct
Available in 1B, 2B, and 6B parameter sizes with unique recency-awareness capabilities for time-sensitive ranking. Only reranker family capable of ranking recent information higher with ~35% performance improvement on recency tasks.
Model Information
- Provider
- Contextual AI
- License
- Proprietary
- Price per 1M tokens
- $0.050
- Release Date
- 2025-09-12
- Model Name
- ctxl-rerank-v2-instruct-multilingual
- Total Evaluations
- 2100
Performance Record
Wins950 (45.2%)
Losses1093 (52.0%)
Ties57 (2.7%)
Wins
Losses
Ties
Performance Overview
ELO ratings by dataset
Contextual AI Rerank v2 Instruct's ELO performance varies across different benchmark datasets, showing its strengths in specific domains.
Contextual AI Rerank v2 Instruct - ELO by Dataset
Detailed Metrics
Dataset breakdown
Performance metrics across different benchmark datasets, including accuracy and latency percentiles.
DBPedia
ELO 156854.9% WR192W-158L-0T
Accuracy Metrics
- nDCG@5
- 0.734
- nDCG@10
- 0.772
- Recall@5
- 0.067
- Recall@10
- 0.108
Latency Distribution
- Mean
- 2803ms
- P50 (Median)
- 2786ms
- P90
- 3138ms
SciFact
ELO 155250.6% WR177W-173L-0T
Accuracy Metrics
- nDCG@5
- 0.867
- nDCG@10
- 0.875
- Recall@5
- 0.916
- Recall@10
- 0.940
Latency Distribution
- Mean
- 3317ms
- P50 (Median)
- 3198ms
- P90
- 4004ms
PG
ELO 149855.7% WR195W-155L-0T
Latency Distribution
- Mean
- 3195ms
- P50 (Median)
- 2951ms
- P90
- 3781ms
business reports
ELO 148041.7% WR146W-202L-2T
Latency Distribution
- Mean
- 2883ms
- P50 (Median)
- 2686ms
- P90
- 3161ms
FiQa
ELO 142431.4% WR110W-230L-10T
Accuracy Metrics
- nDCG@5
- 0.119
- nDCG@10
- 0.125
- Recall@5
- 0.123
- Recall@10
- 0.135
Latency Distribution
- Mean
- 2913ms
- P50 (Median)
- 2863ms
- P90
- 3289ms
MSMARCO
ELO 138537.1% WR130W-175L-45T
Accuracy Metrics
- nDCG@5
- 0.975
- nDCG@10
- 0.975
- Recall@5
- 1.000
- Recall@10
- 1.000
Latency Distribution
- Mean
- 2952ms
- P50 (Median)
- 2853ms
- P90
- 3398ms
Compare Models
See how it stacks up
Compare Contextual AI Rerank v2 Instruct with other top rerankers to understand the differences in performance, accuracy, and latency.