# Cohere Embed 5 launch: ViDoRe V3 parsed-text average

> Cohere launch retrieval report.

Canonical page: https://benchlm.ai/benchmarks/cohereembed5vidorev3

- Category: [external](/external)
- Last updated: September 30, 2026 launch; October 1 capture

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

Eight document domains, using parsed text curated by the ViDoRe authors. Values come from the two launch charts. RCP scores measure reordering a fixed candidate set; they do not measure first-stage retrieval recall.

Cohere reports these results in its Embed 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, and uncertainty intervals are undisclosed.

Each input representation and metric retains its own cohort. RCP-nDCG@10 evaluates reordering a fixed candidate set; it does not measure first-stage retrieval. These provider comparisons do not enter weighted model rankings.

- [Cohere launch and charts](https://cohere.com/blog/embed-5)
- [Embed API model details](https://docs.cohere.com/docs/cohere-embed)
- [Provider full-results sheet (sign-in required at capture)](https://docs.google.com/spreadsheets/d/1HLj1KOjJdFh9bTAc6lbWxG7VfjkRMeE7V11Q0eojtAA/edit?gid=0)
- [RCP-nDCG methodology and annotations](https://github.com/cohere-ai/rcp-ndcg)

## About Cohere Embed 5 launch: ViDoRe V3 parsed-text average

- Year: 2026

Cohere Embed 5 launch: ViDoRe V3 parsed-text average is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (11 configurations)

| Rank | Model | Configuration | Creator | Score |
|------|-------|---------------|---------|-------|
| 1 | [Cohere Embed 5 Pro](https://cohere.com/blog/embed-5) | Cohere provider report; evaluated snapshot and hardware undisclosed | Cohere | 85.8 |
| 2 | [Cohere Embed 5 Fast](https://cohere.com/blog/embed-5) | Cohere provider report; evaluated snapshot and hardware undisclosed | Cohere | 84.5 |
| 3 | [Voyage 4 Large](https://cohere.com/blog/embed-5) | Cohere provider report; evaluated snapshot and hardware undisclosed | Voyage AI | 83.7 |
| 4 | [Gemini Embedding 2](https://cohere.com/blog/embed-5) | Cohere provider report; evaluated snapshot and hardware undisclosed | Google | 83.2 |
| 5 | [Voyage 4 Nano](https://cohere.com/blog/embed-5) | Cohere provider report; evaluated snapshot and hardware undisclosed | Voyage AI | 77.6 |
| 6 | [Cohere Embed 4](https://cohere.com/blog/embed-5) | Cohere provider report; evaluated snapshot and hardware undisclosed | Cohere | 77.0 |
| 7 | [OpenAI text-embedding-3-large](https://cohere.com/blog/embed-5) | Cohere provider report; evaluated snapshot and hardware undisclosed | OpenAI | 75.5 |
| 8 | [Jina Embeddings v5 Text Small](https://cohere.com/blog/embed-5) | Cohere provider report; evaluated snapshot and hardware undisclosed | Jina AI | 74.5 |
| 9 | [Perplexity pplx-embed-v1](https://cohere.com/blog/embed-5) | Cohere provider report; evaluated snapshot and hardware undisclosed | Perplexity | 74.4 |
| 10 | [Microsoft Harrier OSS v1](https://cohere.com/blog/embed-5) | Cohere provider report; evaluated snapshot and hardware undisclosed | Microsoft | 73.4 |
| 11 | [Qwen3-VL-Embedding](https://cohere.com/blog/embed-5) | Cohere provider report; evaluated snapshot and hardware undisclosed | Qwen | 64.2 |

## FAQ

### What does Cohere Embed 5 launch: ViDoRe V3 parsed-text average measure?

Cohere launch retrieval report.

### Which model leads the published Cohere Embed 5 launch: ViDoRe V3 parsed-text average snapshot?

Cohere Embed 5 Pro currently leads the published Cohere Embed 5 launch: ViDoRe V3 parsed-text average snapshot with a score of 85.8.

### How many models are evaluated on Cohere Embed 5 launch: ViDoRe V3 parsed-text average?

The September 30, 2026 launch; October 1 capture contains 11 AI models.

### Does Cohere Embed 5 launch: ViDoRe V3 parsed-text average affect BenchLM's overall score?

Not directly. Cohere Embed 5 launch: ViDoRe V3 parsed-text average is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.