# MiniMax M3.1 Flash Benchmark Scores & Performance

> MiniMax M3.1 Flash by MiniMax scores 67.05/100 overall, ranking #28 out of 955 AI models.

Canonical page: https://benchlm.ai/models/minimax-m3-1-flash

Last updated: October 19, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | MiniMax |
| Source Type | Proprietary |
| Reasoning Type | Reasoning |
| Context Window | 1M |
| Official model card | [MiniMax M3.1 Flash launch post](https://www.minimax.io/blog/minimax-m31f) |
| Overall Score | 67.05/100 |
| Overall Rank | #28 of 955 |

## Family & Coverage

- Family: MiniMax M3.1 Flash
- Variant: flash-reasoning
- Benchmarks covered: 27 of 640
- Sibling models: [MiniMax M3.1 Flash Preview](/models/minimax-m3-1-flash-preview)
- Related earlier model: [MiniMax M3.1 Flash Preview](/models/minimax-m3-1-flash-preview)
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [AutomationBench](/benchmarks/automationbench) | 62.2% | [MiniMax: MiniMax M3.1 Flash](https://www.minimax.io/blog/minimax-m31f) |
| [BankerToolBench](/benchmarks/bankertoolbench) | 76.2% | [MiniMax: MiniMax M3.1 Flash](https://www.minimax.io/blog/minimax-m31f) |
| [Terminal-Bench 4.0](/benchmarks/terminal-bench-4) | 38.10% | [MiniMax: MiniMax M3.1 Flash](https://www.minimax.io/blog/minimax-m31f) |
| [Agents' Last Exam](/benchmarks/agentslastexam) | 29.6% | [MiniMax: MiniMax M3.1 Flash](https://www.minimax.io/blog/minimax-m31f) |
| [OSWorld 2.0](/benchmarks/osworld2) | 61.7% | [MiniMax: MiniMax M3.1 Flash](https://www.minimax.io/blog/minimax-m31f) |
| [CyberGym](/benchmarks/cybergym) | 82.2% | [MiniMax: MiniMax M3.1 Flash](https://www.minimax.io/blog/minimax-m31f) |
| [GDPval-AA](/benchmarks/gdpvalaanormalized) | 47.9% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/minimax-m3-1-flash) |
| [AA Briefcase](/benchmarks/aabriefcaseelo) | 1474 | [Artificial Analysis: aa-briefcase leaderboard](https://artificialanalysis.ai/evaluations/aa-briefcase) |
| [AA AutomationBench](/benchmarks/aaautomationbench) | 72.5% | [Artificial Analysis: automationbench-aa leaderboard](https://artificialanalysis.ai/evaluations/automationbench-aa) |
| [GDPval-AA](/benchmarks/gdpvalaa) | 1458 | [Artificial Analysis: gdpval-aa leaderboard](https://artificialanalysis.ai/evaluations/gdpval-aa) |
| [AA Terminal-Bench 4.0](/benchmarks/terminal-bench-4) | 25.8% | [Artificial Analysis: terminalbench-v4-0 leaderboard](https://artificialanalysis.ai/evaluations/terminalbench-v4-0) |
| [GDP.pdf](/benchmarks/aagdppdf) | 20.8% | [Artificial Analysis: gdp-pdf leaderboard](https://artificialanalysis.ai/evaluations/gdp-pdf) |

## Coding Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [PostTrainBench v1.1](/benchmarks/posttrainbench-v1-1) | 39.3% | [MiniMax: MiniMax M3.1 Flash](https://www.minimax.io/blog/minimax-m31f) |
| [DeepSWE](/benchmarks/deepswe) | 73.7% | [MiniMax: MiniMax M3.1 Flash](https://www.minimax.io/blog/minimax-m31f) |
| [NL2Repo](/benchmarks/nl2repo) | 61.2% | [MiniMax: MiniMax M3.1 Flash](https://www.minimax.io/blog/minimax-m31f) |
| [AA-SciCode](/benchmarks/aascicode) | 53.4% | [Artificial Analysis: scicode leaderboard](https://artificialanalysis.ai/evaluations/scicode) |

## Multimodal & Grounded Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [BabyVision w/ Python](/benchmarks/babyvisionpython) | 91.0% | [MiniMax: MiniMax M3.1 Flash](https://www.minimax.io/blog/minimax-m31f) |
| [CharXiv](/benchmarks/charxiv) | 82.5% | [MiniMax: MiniMax M3.1 Flash](https://www.minimax.io/blog/minimax-m31f) |
| [AA-MMMU-Pro](/benchmarks/mmmu-pro) | 79.1% | [Artificial Analysis: mmmu-pro leaderboard](https://artificialanalysis.ai/evaluations/mmmu-pro) |

## Reasoning Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [AA-LCR](/benchmarks/lcr) | 79.7% | [Artificial Analysis: artificial-analysis-long-context-reasoning leaderboard](https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning) |
| [CritPt](/benchmarks/critpt) | 22.3% | [Artificial Analysis: critpt leaderboard](https://artificialanalysis.ai/evaluations/critpt) |

## Knowledge Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [HLE w/o tools](/benchmarks/hlenotools) | 43.4% | [MiniMax: MiniMax M3.1 Flash](https://www.minimax.io/blog/minimax-m31f) |
| [Artificial Analysis Intelligence Index](/benchmarks/artificialanalysis) | 42.4% | [Artificial Analysis: artificial-analysis-intelligence-index leaderboard](https://artificialanalysis.ai/evaluations/artificial-analysis-intelligence-index) |
| [AA-HLE](/benchmarks/aahle) | 48.0% | [Artificial Analysis: humanitys-last-exam leaderboard](https://artificialanalysis.ai/evaluations/humanitys-last-exam) |
| [AA-Omniscience Index](/benchmarks/aaomniscienceindex) | 15.6% | [Artificial Analysis: omniscience leaderboard](https://artificialanalysis.ai/evaluations/omniscience) |
| [AA-Omniscience Accuracy](/benchmarks/omniscienceaccuracy) | 56.2% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/minimax-m3-1-flash) |
| [AA-Omniscience Hallucination Rate](/benchmarks/omnisciencehallucinationrate) | 92.8% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/minimax-m3-1-flash) |

## Other MiniMax Models

- [MiniMax M3](/models/minimax-m3) - Score: 54.96
- [MiniMax M2.5](/models/minimax-m2-5) - Score: 49.94
- [MiniMax M2.7](/models/minimax-m2-7) - Score: 48.17
- [MiniMax M1 80k](/models/minimax-m1-80k) - Score: 27.55
- [MiniMax M3.1 Flash Preview](/models/minimax-m3-1-flash-preview) - Score: not computed
- [MiniMax Speech 2.8 HD](/models/minimax-speech-2-8-hd) - Score: not computed
- [MiniMax Speech-02 HD](/models/minimax-speech-02-hd) - Score: not computed