# MRCR 1M

> A million-token MRCR long-context retrieval benchmark reported in DeepSeek-V4 model evaluations.

Canonical page: https://benchlm.ai/benchmarks/mrcr1m

- Category: [Reasoning](/reasoning)
- Last updated: September 15, 2026

## About MRCR 1M

- Year: 2026
- Tasks: Million-token retrieval
- Format: Long-context retrieval MMR
- Difficulty: Million-token long context
- Paper: [DeepSeek-V4 Technical Report](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/DeepSeek_V4.pdf)

BenchLM stores this DeepSeek-reported MRCR 1M value as a display-only row distinct from the existing MRCRv2 keys.

MRCR 1M is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (4 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [DeepSeek V4 Pro 0813](/models/deepseek-v4-pro-0813) | DeepSeek | 83.5% |
| 2 | [DeepSeek V4 Flash 0731](/models/deepseek-v4-flash-0731) | DeepSeek | 78.7% |
| 3 | [Muse Spark 1.1](/models/muse-spark-1-1) | Meta | 54.1% |
| 4 | [Gemini 3.5 Flash](/models/gemini-3-5-flash) | Google | 26.6% |

## FAQ

### What does MRCR 1M measure?

A million-token MRCR long-context retrieval benchmark reported in DeepSeek-V4 model evaluations.

### Which model scores highest on MRCR 1M?

DeepSeek V4 Pro 0813 by DeepSeek currently leads with a score of 83.5% on MRCR 1M.

### How many models are evaluated on MRCR 1M?

4 AI models have been evaluated on MRCR 1M on BenchLM.

### Does MRCR 1M affect BenchLM's overall score?

Not directly. MRCR 1M is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Compare Top Models on MRCR 1M

- [DeepSeek V4 Pro 0813 vs DeepSeek V4 Flash 0731](/compare/deepseek-v4-flash-0731-vs-deepseek-v4-pro-0813)
- [DeepSeek V4 Flash 0731 vs Muse Spark 1.1](/compare/deepseek-v4-flash-0731-vs-muse-spark-1-1)
- [Muse Spark 1.1 vs Gemini 3.5 Flash](/compare/gemini-3-5-flash-vs-muse-spark-1-1)