**MiniMax-M3.1-Flash** is a native multimodal mixture-of-experts model for coding, agentic workflows, computer use, and cybersecurity. It supports text, image, and video inputs with a context window of up to **1M tokens**. Building on MiniMax-M3, M3.1-Flash improves task performance and inference efficiency with sparse attention throughout the model, quantization-aware training, and DSpark speculative decoding. **Highlights:** - **Agentic performance:** A generational leap in agentic tasks, coding, and cybersecurity — 76.2 on BankerToolBench, 73.7% on DeepSWE v1.1, 61.7 on OSWorld V2, 29.6 on Agents' Last Exam, and 82.2 on CyberGym. - **Efficient by design:** Sparse attention throughout, quantization-aware training, and DSpark speculative decoding improve inference efficiency. ## Model at a Glance - **Architecture:** Native multimodal mixture-of-experts (MoE) - **Parameters:** Approximately 428B total; 23B activated per token - **Inputs / output:** Text, image, and video inputs; text output - **Context window:** Up to 1,000,000 tokens - **Attention:** [MiniMax Sparse Attention](https://arxiv.org/abs/2606.13392) (MSA) throughout the model - **Speculative decoding:** DSpark draft head included ## Benchmarks

Benchmark	MiniMax M3.1 Flash	DeepSeek V4.1 Flash-1017	DeepSeek V4.1 Flash	Kimi K3	GLM-5.3	GPT-5.6 Sol	Opus 5
Automation-Bench v1.0.6	62.8	60.5	54.8	46.7	48.8	45.8	50.3
BankerToolBench	76.2	—	73.7	69.1	74.5	74.6	76.2
GDP.pdf AA	20.8	—	12.8	22.0	11.2	27.2	21.6
Terminal Bench 4.0	38.1	42.3	31.2	12.6	37.9	39.9	51.8
LOCA-Bench 256K	60.3	—	—	49.7	50.3	60.0	53.7
Agents’ Last Exam	29.6	—	—	28.3	—	30.6	32.2
OSWorld 2.0	61.7	—	54.3	58.3	—	65.7	70.6
PostTrain Bench v1.1	39.3	—	30.5	36.6	37.5	36.2	40.4
DeepSWE v1.1	73.7	77.0	74.2	67.5	66.9	73.0	74.0
NL2Repo-Bench	61.2	68.2	65.4	58.0	58.0	56.8	75.3
SWE Refactor Bench	23.0	—	11.8	19.5	10.4	28.5	31.0
CyberGym	82.2	—	—	80.0	84.5	83.6	—
BabyVision (with tools)	91.0	92.5	89.6	85.7	—	88.9	94.1
HLE (without tools)	43.4	42.6	39.2	43.5	42.3	49.5	55.6
CharXiv RQ	82.5	—	69.0	84.8	—	85.2	83.7

Evaluation Notes

- **Automation-Bench v1.0.6:** 600 publicly released tasks. - **BankerToolBench:** OpenCode 1.17.18; MiniMax-M2.7 judge. - **GDP.pdf AA:** Taken directly from Artificial Analysis. - **Terminal Bench 4.0:** Codex 0.149.1. - **LOCA-Bench 256K:** Official implementation. - **Agents’ Last Exam:** Official Overall setting; full-set results from the official ALE leaderboard only. Blank = no official result (CLI-only excluded), not zero. - **OSWorld 2.0:** 0808 Full release; highest reported per model at release, except DeepSeek V4.1 (in-house reproduction). - **PostTrain Bench v1.1:** Claude Code 2.1.251, 512K context; otherwise official setup. - **DeepSWE v1.1:** mini-SWE-agent 2.4.5, 512K context. - **NL2Repo-Bench:** Claude Code 2.1.233, 512K context; reward hacking = 0; two inconsistent tasks corrected (scores use the corrected set). - **SWE Refactor Bench:** Claude Code 2.1.220, 200K context; otherwise official setup. - **CyberGym:** Claude Code 2.1.263, 1M context. - **BabyVision (with tools):** Claude Code 2.1.285; min image side 1,500 px. - **HLE (without tools):** Text-only subset (2,158 questions). - **CharXiv RQ:** GPT-5.5 judge.

Results are for the official weights; third-party quantizations may differ. ## What’s New in M3.1-Flash M3.1-Flash retains M3’s core mixture-of-experts architecture, with three main changes: - **Sparse attention throughout:** the first three full-attention layers are replaced with sparse attention. - **Quantization-aware training:** the routed MoE experts and the attention paths are quantized during training, reducing memory footprint and improving serving efficiency. - **DSpark speculative decoding:** DSpark replaces the earlier EAGLE-like MTP approach. The release includes the draft head for use with compatible serving implementations. ## How to Use - [MiniMax Code](https://agent.minimax.io/) - [MiniMax API](https://platform.minimax.io/) ### Local Deployment Download the model: ```bash hf download MiniMaxAI/MiniMax-M3.1-Flash --local-dir MiniMax-M3.1-Flash ``` We recommend the following inference frameworks to serve the model: - [SGLang](https://docs.sglang.io/) — see [SGLang cookbook](https://docs.sglang.io/cookbook/autoregressive/MiniMax/MiniMax-M3.1). - [vLLM](https://github.com/vllm-project/vllm) — see [vLLM recipe](https://recipes.vllm.ai/MiniMaxAI/MiniMax-M3.1-Flash). - [TokenSpeed](https://github.com/lightseekorg/tokenspeed) — see [TokenSpeed recipe](https://lightseek.org/tokenspeed/recipes/models#minimax-m3-1). Additional integrations in progress: Transformers, KTransformers, unsloth, and ATOM. ### Multi-Chip Deployment [FlagOS](https://github.com/flagos-ai) — see [Multi-Chip Support and Downloads](https://huggingface.co/MiniMaxAI/MiniMax-M3.1-Flash/blob/main/docs/FlagOS-Multi-Chip-Support-and-Downloads.md). ## Inference Settings Recommended sampling settings: `temperature=1.0` and `top_p=0.95`. For reasoning, set `reasoning_effort` in the chat template: `low`, `medium`, `high`, `xhigh`, or `max`. The model supports a context window of up to 1M tokens. Usable context length and throughput depend on GPU memory and the serving configuration. ## Contact Us Contact us at [model@minimax.io](mailto:model@minimax.io).

Full Model Card (README)