Skip to main content
BenchLM
Advertise

Benchmark profile

MRCR 1M

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

Data verified

Benchmark score on MRCR 1M — July 23, 2026

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

1Open

DeepSeek V4 Pro (Max)

DeepSeek

deepseek-v4-pro-max

83.5%
Overall —Context 1M
2Open

DeepSeek V4 Pro (High)

DeepSeek

deepseek-v4-pro-high

83.3%
Overall 55.47Context 1M
3Open

DeepSeek V4 Flash (Max)

DeepSeek

deepseek-v4-flash-max

78.7%
Overall —Context 1M
8 modelsReasoningCurrentDisplay onlyUpdated July 23, 2026

Benchmark score table (8 models)

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

The published MRCR 1M snapshot places DeepSeek V4 Pro (Max) 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.

DeepSeek-V4 Technical Report

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 (Max) 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.

Compare Top Models on MRCR 1M

DeepSeek V4 Pro (Max) vs DeepSeek V4 Pro (High)DeepSeek V4 Pro (High) vs DeepSeek V4 Flash (Max)DeepSeek V4 Flash (Max) vs DeepSeek V4 Flash (High)DeepSeek V4 Flash (High) vs Muse Spark 1.1
Last updated: July 23, 2026 · BenchLM version MRCR 1M 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.