Skip to main content
Radar

Every change to the models you run, with its source and its date. Releases, price changes, retirements, API changes, and incidents.Every change to the models you run, with its source.

Follow model changes

MRCR 1M

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

Data verified 33 confirmed releases in the last 30 daysSee provider release alerts

Benchmark score on MRCR 1M — September 15, 2026

We mirror the published score view for MRCR 1M. DeepSeek V4 Pro 0813 leads the public snapshot at 83.5%, followed by DeepSeek V4 Pro (High) (83.3%) and DeepSeek V4 Flash 0731 (78.7%). We do not use these results to rank models overall.

8 modelsReasoningCurrentDisplay onlyUpdated September 15, 2026

Benchmark score table (8 models)

Score
1
DeepSeek V4 Pro 0813DeepSeek · Closed
83.5%
2
DeepSeek V4 Pro (High)DeepSeek · Open weight
83.3%
3
DeepSeek V4 Flash 0731DeepSeek · Closed
78.7%
4
DeepSeek V4 Flash (High)DeepSeek · Closed
76.9%
5
Muse Spark 1.1Meta · Closed
54.1%
6
DeepSeek V4 ProDeepSeek · Open weight
44.7%
7
DeepSeek V4 FlashDeepSeek · Closed
37.5%
8
Gemini 3.5 FlashGoogle · Closed
26.6%

The published MRCR 1M snapshot places DeepSeek V4 Pro 0813 first at 83.5%. The third row is 4.8 points behind. The broader top-10 range is 56.9 points, so the table still separates the published systems.

8 models have been evaluated on MRCR 1M. The benchmark falls in the Reasoning category. This category carries a 17% weight in BenchLM.ai's overall scoring system. MRCR 1M is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About MRCR 1M

Year

2026

Tasks

Million-token retrieval

Format

Long-context retrieval MMR

Difficulty

Million-token long context

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

BenchLM freshness & provenance

Version

MRCR 1M 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

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?

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

Last updated: September 15, 2026 · BenchLM version MRCR 1M 2026

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.