Alternatives

Products that do what MiniMax M2.5 does

The first open model to beat Sonnet made for productivity

1. 1
   MiniCPM5-1B▲96

   A new SOTA for compact open models on the edge

   May 2026

2. 2
   Maxclaw on Mobile▲138

   Build apps, research deeply and automate multi-step tasks

   Mar 2026

3. 3
   Kimi K2 Thinking▲209

   The 1T Parameters Open-Source Thinking Model - SOTA on HLE

   Nov 2025

4. 4
   GLM-5▲154

   Open-weights model for long-horizon agentic engineering

   Feb 2026

5. 5
   Dream 7B▲191

   Powerful Open Diffusion LLM, Beyond Autoregressive

   2025

6. 6
   MaxClaw by MiniMax▲124

   Always-on managed agent based on OpenClaw powered by MiniMax

   Feb 2026

7. 7
   Qwen3.6-27B▲120

   The sweet-spot open dense model for coding agents

   Apr 2026

8. 8
   MiniCPM 4.1▲116

   The on-device model for your personal data

   Sep 2025

9. 9
   Qwen3.6-35B-A3B▲124

   The open sparse MoE model for agentic coding

   Apr 2026

10. 10
    Mellum by JetBrains▲197

    Fast LLMs for low-latency and high-performance workflows

    Jun 2026

11. 11
    OpenCode Superapp▲128

    The power of Codex with local, self-hosted models and voice

    Jul 2026 · opencodesuper.app

12. 12
    Nemotron 3 Ultra by NVIDIA▲179

    Powers faster, efficient reasoning for long-running agents

    Jun 2026

13. 13
    MiniCPM 4.0▲110

    Ultra-efficient on-device AI, now even faster

    2025

14. 14
    GPT-5▲127

    OpenAI’s most advanced model

    2025

15. 15
    MaxHermes by Minimax▲120

    AI agent that builds skills from every task you give it

    Apr 2026

16. 16
    Devstral 2▲190

    SOTA open-source agentic coding models and CLI agent

    Dec 2025

17. 17
    Inkling▲181

    Open weights 975B multimodal model built for fine-tuning

    Jul 2026

18. 18
    MiniMax Hub▲78

    Desktop AI workstation with agent-driven visual canvas

    May 2026

19. 19
    MiniCPM-V 4.5▲93

    GPT-4o level vision model on the phone

    2025

20. 20
    MiniCPM-V 4.6▲98

    Ultra-efficient 1.3B vision-language model for mobile

    May 2026

21. 21
    Qwen2.5-Max▲59

    Large language model series developed by Alibaba Cloud

    2025

22. 22
    Miniloop▲80

    Turn natural language into AI agents and automations

    Feb 2026

23. 23RS
    Randomly switching between LMs at every step boosts SWE-bench score▲5

    What if your agent uses a different LM at every turn? We let mini-SWE-agent randomly switch between GPT-5 and Sonnet 4 and it scored higher on SWE-bench than with either model separately. GPT-5 by itself gets 65.0%, Sonnet 4 64.8%, but randomly switching at every step gets us 67.2% This result came pretty surprising to us. There's a few more experiments in the blog post.

    2025 · swebench.com

24. 24MS
    Mini-swe-agent achieves 65% on SWE-bench in 100 lines of python▲7

    2025 · github.com

Ranked by how close each launch is in meaning, then by votes. Refine with a description →