---
last_updated: 2026-11-21
source_url: https://opper.ai/minimax/minimax-m1-80k
title: "MiniMax-M1-80k by MiniMax"
description: "MiniMax M1: open-weight hybrid-attention reasoning model with 1M context, 456B parameters, and an 80K-token thinking budget"
---

# MiniMax-M1-80k

By [MiniMax](https://opper.ai/minimax).

MiniMax M1 is described by its maker as the world's first open-weight, large-scale hybrid-attention reasoning model, featuring 456 billion total parameters with 45.9 billion activated per token. Released in June 2025 under the Apache 2.0 license, it pairs a 1M-token context window with a hybrid Mixture-of-Experts architecture and a Lightning Attention mechanism.

The model scores 56.0% on SWE-bench (software engineering) and 86.0% on AIME 2024 (mathematics), and leads open-weight models on tool-use benchmarks such as TAU-bench. At 80K-token reasoning lengths, Lightning Attention uses roughly 30% of the compute that DeepSeek R1 requires, enabling efficient scaling of test-time compute across deep reasoning and long-context tasks.

The 80K variant provides an 80,000-token reasoning budget for extended thinking. MiniMax trained M1 with CISPO, a reinforcement learning algorithm it reports converges about twice as fast as alternatives, completing training in three weeks on 512 H800 GPUs.

## Key info

- Input: Text
- Output: Text
- Features: Reasoning, Tools
- Context window: 1M
- Max output: 40K

## Benchmarks

Independent benchmark scores via [Artificial Analysis](https://artificialanalysis.ai) ([view on AA](https://artificialanalysis.ai/models/minimax-m1-80k)). Indices and domain scores are out of 100, Omniscience runs from −100 to 100, Briefcase is an Elo rating, and the other evaluation scores are the share of tasks solved.

- Global rank: #254 of 520 LLMs on the [LLM leaderboard](https://opper.ai/llm-leaderboard)
- Tier: Efficient
- Output speed: 52 tok/s
- Intelligence Index (previous version): 11.7

### Coding

- LiveCodeBench: 71%

### Agentic & knowledge work

- Terminal-Bench Hard: 3%
- τ²-Bench Telecom: 34%

### Science & reasoning

- Humanity's Last Exam: 9%
- GPQA Diamond: 70%
- Long-context reasoning: 58%

### Knowledge

- MMLU-Pro: 82%

### Math & instruction following

- AIME 2025: 61%
- IFBench: 42%

## Available routes

No routes currently available — MiniMax-M1-80k isn't routed through the Opper gateway right now. It may return. Contact [hello@opper.ai](mailto:hello@opper.ai) about this model.

## Available models from MiniMax

- [MiniMax M3.1 Flash](https://opper.ai/minimax/minimax-m3-1-flash)
- [MiniMax M3](https://opper.ai/minimax/minimax-m3)
- [MiniMax M2.5](https://opper.ai/minimax/minimax-m2-5)
- [MiniMax M2.7](https://opper.ai/minimax/minimax-m2-7)
- [MiniMax H3](https://opper.ai/minimax/minimax-h3)
- [MiniMax H3 Max](https://opper.ai/minimax/minimax-h3-max)
