llmboard.aiAI model intelligence
Home

Model Rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision
Image GenerationImage Editing
Video GenerationImage to VideoVideo Editing
Text to SpeechSpeech to Text
Embeddings

Efficiency

Chat Token PricingImage PricingVideo PricingAudio Pricing
Chat Speed & LatencyProvider Reliability

Benchmarks

GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-Pro
All Benchmarks

Tools

Model DirectoryCompare Models

Scoring & Data

Scoring & Data
393 models668 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll BenchmarksReasoningMath

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai

long context benchmark

MRCR 1M Leaderboard

MRCR 1M is a variant of the Multi-Round Coreference Resolution benchmark designed for testing extremely long context capabilities with approximately 1 million tokens. It evaluates models' ability to maintain reasoning and attention across ultra-long conversations.

Updated Aug 17, 2026

Models4
Model coverage4
MetricScore
EvidenceB

On this page

  • Ranking
  • Highlights
  • Distribution
  • Top models
  • About
  • FAQ

MRCR 1M Ranking

Higher score ranks better on this benchmark.

4 rows
Columns

Show columns

Sort by
Rank
Model
Score
Percentile
Participants
Evidence
Evaluated
Rank01ModelDEDeepSeek-V4-Pro-MaxDeepSeekScore83.5%Percentile100.0%Participants4EvidenceCEvaluatedAug 17, 2026
Rank02ModelDEDeepSeek-V4-Flash-MaxDeepSeekScore78.7%Percentile66.7%Participants4EvidenceCEvaluatedAug 17, 2026
Rank03ModelDEDeepSeek-V4-Flash-0423DeepSeekScore76.9%Percentile33.3%Participants4EvidenceCEvaluatedAug 17, 2026
Rank04ModelGOGemini 2.0 Flash-LiteGoogleScore58.0%Percentile0.0%Participants4EvidenceCEvaluatedAug 17, 2026

MRCR 1M Highlights

The leading models and scores on this benchmark.

Rank #1DeepSeek-V4-Pro-Max83.5%Rank #2DeepSeek-V4-Flash-Max78.7%Rank #3DeepSeek-V4-Flash-042376.9%Rank #4Gemini 2.0 Flash-Lite58.0%

MRCR 1M Score Distribution

A closer view of the leading scores on this benchmark.

MRCR 1M

The Top AI Models for MRCR 1M

The first five results on this benchmark, with official price and output speed added where the model identity can be matched.

Ranking basisThis mrcr 1m AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.

  1. 01
    DE
    DeepSeek-V4-Pro-MaxDeepSeek
    Score
    83.5%
    Price
    $0.43 input / $0.87 output per 1M tokens
    Speed
    Up to 18 tok/s via Fireworks

    Strengths

    • Ranks #1 of 4 compared models
    • 100th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures MRCR 1M, not total model capability
  2. 02
    DE
    DeepSeek-V4-Flash-MaxDeepSeek
    Score
    78.7%
    Price
    $0.14 input / $0.28 output per 1M tokens
    Speed
    Up to 19 tok/s via Novita

    Strengths

    • Ranks #2 of 4 compared models
    • 67th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures MRCR 1M, not total model capability
  3. 03
    DE
    DeepSeek-V4-Flash-0423DeepSeek
    Score
    76.9%
    Price
    $0.14 input / $0.28 output per 1M tokens
    Speed
    Up to 19 tok/s via Novita

    Strengths

    • Ranks #3 of 4 compared models
    • 33th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures MRCR 1M, not total model capability
  4. 04
    GO
    Gemini 2.0 Flash-LiteGoogle
    Score
    58.0%
    Speed
    Up to 85 tok/s via Google

    Strengths

    • Ranks #4 of 4 compared models
    • 0th percentile on this benchmark
    • C evidence result

    Considerations

    • This result measures MRCR 1M, not total model capability

Selection summary

Best AI Models for MRCR 1M

DeepSeek-V4-Pro-Max currently leads MRCR 1M with 83.5%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.

Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.

Benchmark rank #1DeepSeek-V4-Pro-Max83.5% · $0.43 input / $0.87 output per 1M tokensBenchmark rank #2DeepSeek-V4-Flash-Max78.7% · $0.14 input / $0.28 output per 1M tokensBenchmark rank #3DeepSeek-V4-Flash-042376.9% · $0.14 input / $0.28 output per 1M tokens

What is MRCR 1M?

What MRCR 1M measures and how its scores work.

MRCR 1M is a variant of the Multi-Round Coreference Resolution benchmark designed for testing extremely long context capabilities with approximately 1 million tokens. It evaluates models' ability to maintain reasoning and attention across ultra-long conversations.

Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.

Family
MRCR 1M
Modality
text
Primary category
long context
Score direction
higher
LLMBoard eligible
Yes
Evaluation key
mrcr-1m|llm-stats-current

Benchmark scores retain their original unit. Overall score eligibility is shown separately.

FAQ

Common questions about MRCR 1M.

Which model scores highest on MRCR 1M?

DeepSeek-V4-Pro-Max is currently ranked first with 83.5%.

What does MRCR 1M measure?

MRCR 1M is a variant of the Multi-Round Coreference Resolution benchmark designed for testing extremely long context capabilities with approximately 1 million tokens. It evaluates models' ability to maintain reasoning and attention across ultra-long conversations.

Is a higher score better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

4 model results are currently shown.

Does this benchmark affect the overall score?

Yes. This benchmark can contribute to the current LLMBoard capability score.