# Cohere Rerank 5 launch: Parsed PDFs average

> Cohere launch reranking report.

Canonical page: https://benchlm.ai/benchmarks/coherererank5parsedpdf

- Category: [external](/external)
- Last updated: October 21, 2026 launch; November 4 capture

Evaluation results published by [Cohere](https://cohere.com/blog/rerank-5). undefined

Average across 47 datasets of text parsed from PDFs with Gemini 1.5 Flash. Values match the launch text and chart labels.

Cohere reports these results in its Rerank 5 launch. The linked full spreadsheet requires sign-in at capture, so this view includes only exact figures available in the public post. Model snapshots, evaluation dates, candidate-set sizes, and uncertainty intervals are undisclosed.

Each metric retains its own cohort. Rerankers reorder candidates from a first-stage search; these scores do not measure embedding or keyword retrieval on their own. These provider comparisons do not enter weighted model rankings.

- [Cohere launch and charts](https://cohere.com/blog/rerank-5)
- [Rerank API model details](https://docs.cohere.com/docs/rerank)
- [OpenRouter availability (November 4, 2026)](https://docs.cohere.com/changelog/embed-rerank-v5-openrouter)
- [Provider full-results sheet (sign-in required at capture)](https://docs.google.com/spreadsheets/d/1FYXax6vFdKE4ph3eXj935jCl7mpeczvYe5jye2h1f9U/edit?gid=0)
- [RCP-nDCG methodology and annotations](https://github.com/cohere-ai/rcp-ndcg)

## About Cohere Rerank 5 launch: Parsed PDFs average

- Year: 2026

Cohere Rerank 5 launch: Parsed PDFs average is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (7 configurations)

| Rank | Model | Configuration | Creator | Score |
|------|-------|---------------|---------|-------|
| 1 | [Cohere Rerank 5 Pro](https://cohere.com/blog/rerank-5) | Cohere provider report; evaluated snapshot and hardware undisclosed | Cohere | 89.9 |
| 2 | [Cohere Rerank 5 Fast](https://cohere.com/blog/rerank-5) | Cohere provider report; evaluated snapshot and hardware undisclosed | Cohere | 88.5 |
| 3 | [Voyage AI Rerank 3](https://cohere.com/blog/rerank-5) | Cohere provider report; evaluated snapshot and hardware undisclosed | Voyage AI | 88.4 |
| 4 | [Cohere Rerank 4 Pro](https://cohere.com/blog/rerank-5) | Cohere provider report; evaluated snapshot and hardware undisclosed | Cohere | 88.3 |
| 5 | [Voyage AI Rerank 3 Lite](https://cohere.com/blog/rerank-5) | Cohere provider report; evaluated snapshot and hardware undisclosed | Voyage AI | 86.0 |
| 6 | [Qwen3-Reranker-8B](https://cohere.com/blog/rerank-5) | Cohere provider report; evaluated snapshot and hardware undisclosed | Qwen | 83.8 |
| 7 | [Qwen3-Reranker-0.6B](https://cohere.com/blog/rerank-5) | Cohere provider report; evaluated snapshot and hardware undisclosed | Qwen | 75.7 |

## FAQ

### What does Cohere Rerank 5 launch: Parsed PDFs average measure?

Cohere launch reranking report.

### Which model leads the published Cohere Rerank 5 launch: Parsed PDFs average snapshot?

Cohere Rerank 5 Pro currently leads the published Cohere Rerank 5 launch: Parsed PDFs average snapshot with a score of 89.9.

### How many models are evaluated on Cohere Rerank 5 launch: Parsed PDFs average?

The October 21, 2026 launch; November 4 capture contains 7 AI models.

### Does Cohere Rerank 5 launch: Parsed PDFs average affect BenchLM's overall score?

Not directly. Cohere Rerank 5 launch: Parsed PDFs average is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.