github.com/MiroMindAI/MiroThinker @main

🚀 Try MiroThinker!

MiroThinker: A deep research agent optimized for research and prediction. It achieves a 88.2 on the challenging BrowseComp benchmark. See Quick Start.

📋 Table of Contents

• 📰 News & Updates
• 📝 Introduction
• ✨ Key Features
• 📈 Performance on Benchmarks
• 🚀 Quick Start
• 📊 Benchmark Evaluation
• 🔬 Trace Collection
• ❓ FAQ & Troubleshooting
• 📄 License
• 🙏 Acknowledgments

📰 News & Updates

• [2026-03-11] 🎉🎉🎉 Introducing MiroThinker-1.7, including MiroThinker-1.7-mini and MiroThinker-1.7. MiroThinker-1.7-mini achieves 72.3 on BrowseComp-ZH, setting a new SOTA among open-source models while using only 30B parameters. Our proprietary agent MiroThinker-H1 achieves leading performance on BrowseComp and BrowseComp-ZH among open-source and commercial models.
• [2026-01-23] 🎉 We have brought two important updates to MiroThinker online: (a) Core Research Report Generation: Deep Research online reports now support generation, preview, and sharing. (b) Extended Document Upload Types: Now supports the upload of various file formats, such as .pdf, .doc, .ppt, .xls, .jpg. Welcome to try it out! MiroThinker will continue to be maintained and iteratively upgraded, with the goal of becoming the best Research Agent you'll ever use!
• [2026-01-05] 🎉🎉 We release MiroThinker-v1.5, a series of open-source deep research agents optimized for financial prediction. MiroThinker-v1.5-30B surpasses Kimi-K2-Thinking on BrowseComp-ZH at much lower cost, using only 1/30 of the parameters. MiroThinker-v1.5-235B scores 39.2% on HLE-Text, 69.8% on BrowseComp, 71.5% on BrowseComp-ZH, and 80.8% on GAIA-Val-165, setting a new state-of-the-art among search agents.

📜 Click to expand older updates

• [2025-11-13] 🎉 MiroThinker-v1.0 is now released! Introducing interactive scaling as a third dimension of performance improvement, MiroThinker v1.0 supports 256K context window and up to 600 tool calls per task. Available in 8B, 30B, and 72B parameter scales, achieving 37.7%, 47.1%, 55.6%, and 81.9% on HLE-Text, BrowseComp, BrowseComp-ZH, and GAIA-Text-103, respectively. See Technical Report for more details.
• [2025-09-11] MiroThinker-72B-Preview ranked 4th in this week's FutureX benchmark. See FutureX.
• [2025-09-08] MiroThinker-v0.2 is now released, achieving open-source SOTA performance across multiple benchmarks, including HLE (17.8%), HLE-Text-Only (19.1%), BrowseComp-EN (17.2%), BrowseComp-ZH (29.4%), XBench-DeepSearch (56.0%), and Frames (74.8%).
• [2025-09-07] We supported more benchmarks, including BrowseComp-ZH, XBench-DeepSearch, and FutureX. We plan to add more benchmarks in the future.
• [2025-08-22] Introducing streamlined deployment options for MiroThinker with optimized resource usage and faster startup times. Experience the interactive demo: 🚀 Try Gradio Demo
• [2025-08-08] MiroThinker-v0.1 released.

📝 Introduction

MiroThinker-1.7

Our new MiroThinker family represents a significant leap in building reliable agents for long-chain tasks. Engineered with enhanced post-training pipeline, our MiroThinker-1.7 family achieve SOTA performance in deep research tasks among open-source models.

Key Features

• 🚀 MiroThinker-1.7 supports a 256K context window, long-horizon reasoning, and deep multi-step analysis.
• 🔧 Handles up to 300 tool interactions per task, now with more accurate stepwise reasoning and decision-making.
• 📦 Released in 30B and 235B parameter scales, accompanied by a comprehensive suite of tools and workflows to flexibly support diverse research settings and compute budgets.
• Our proprietary agent, MiroThinker-H1 provides promising evidence for long-chain verifiable reasoning — reasoning processes that are step-verifiable and globally verifiable, improving the performance of complex agentic workflows.

MiroThinker-1.7 demonstrates strong general-research performance across a broad range of benchmarks, achieving 74.0%, 75.3%, 82.7% and 42.9% on BrowseComp, BrowseComp-ZH, GAIA-Val-165 and HLE-Text, respectively. MiroThinker-1.7 achieves SOTA performance on BrowseComp-ZH.

MiroThinker-v1.5

📦 Click to expand MiroThinker-v1.5 details

MiroThinker v1.5 is the world-leading open-source search agent that advances tool-augmented reasoning through interactive scaling — training the agent to handle deeper and more frequent agent-environment interactions as a third dimension of performance improvement, beyond model size and context length.

Key Features

• 🚀 MiroThinker v1.5 supports a 256K context window, long-horizon reasoning, and deep multi-step analysis.
• 🔧 Handles up to 400 tool calls per task — a substantial improvement over previous open-source research agents.
• 📦 Released in 30B and 235B parameter scales, accompanied by a comprehensive suite of tools and workflows to flexibly support diverse research settings and compute budgets.

MiroThinker v1.5 demonstrates strong general-research performance across a broad range of benchmarks, achieving 39.2%, 69.8%, 71.5%, and 80.8% on HLE-Text, BrowseComp, BrowseComp-ZH, and GAIA-Val-165, respectively. These results surpass previous open-source agents and set the new world-leading BrowseComp performance.

MiroThinker-v1.0

📦 Click to expand MiroThinker-v1.0 details

Unlike previous agents that scale only model size or context length, MiroThinker v1.0 introduces interactive scaling at the agent level, systematically training the agent to handle deeper and more frequent agent–environment interactions as a third dimension of performance improvement. Interactive scaling leverages environment feedback and external information acquisition to correct errors and refine trajectories.

✨ Key Features

• 🚀 256K Context Window: Supports long-horizon reasoning and deep multi-step analysis
• 🔧 600 Tool Calls: Handles up to 600 tool calls per task — a substantial improvement over previous open-source research agents
• 📦 Multiple Scales: Released in 8B, 30B, and 72B parameter scales, accompanied by a comprehensive suite of tools and workflows to flexibly support diverse research settings and compute budgets

MiroThinker v1.0 demonstrates strong general-research performance across a broad range of benchmarks, achieving 37.7%, 47.1%, 55.6%, and 81.9% on HLE-Text, BrowseComp, BrowseComp-ZH, and GAIA-Text-103, respectively. These results surpass previous open-source agents and narrow the gap with commercial counterparts such as GPT-5-high.

MiroThinker-v0.2

📦 Click to expand MiroThinker-v0.2 details

In this new version, we introduced three key improvements:

• 📚 Richer training data from both English and Chinese sources, yielding significant gains in benchmark performance and generalization
• 🎯 Unified DPO training with a single preference dataset across all agents
• 📏 Extended context length from 40k to 64k for more challenging multi-turn tool-use tasks

Compared to v0.1, MiroThinker v0.2 delivers consistent gains across benchmarks. For example, scores improved from 57.3 → 64.1 on GAIA-Text-103 and from 17.0 → 29.4 on BrowseComp-ZH, reflecting substantial advancements in the model’s general research agent capabilities.

MiroThinker-v0.1

📦 Click to expand MiroThinker-v0.1 details

<img src="https://github.com/MiroMindAI/MiroThinker/raw/main/assets/gaia_text_103.png" width="98%" alt="MiroFlow Performance on GAI