MiMo V2.5 Pro
LLM Provider / Model · Highest open-weight coding performance, 1M context agentic tasks, complex multi-step engineering, long-context reasoning
At a glance
| Input price | Free (self-hosted) |
| Output price | Free (self-hosted) |
| Price tier | Free |
| Context window | 1M+ |
| Max output | 32K |
| Context tier | 500K+ |
| Speed tier | Standard |
| Latency | local-bound |
| Knowledge cutoff | 2026 |
| Modality | Text-only |
| Model ID | mimo-v2.5-pro |
| Provider | Xiaomi |
| HumanEval | 76% |
| MMLU | 89% |
| SWE-Bench | 79% |
| Benchmark | SWE-bench: top |
| Released | 2026 |
| Hosting | Open-weights |
| Capabilities | Tool use, Streaming, Structured output, Agentic coding, Extended reasoning, Multi-Token Prediction (3 layers), Hybrid attention (SWA + Global), Long context (1M), Self-hostable |
What MiMo V2.5 Pro does
Tool use, Streaming, Structured output, Agentic coding, Extended reasoning, Multi-Token Prediction (3 layers), Hybrid attention (SWA + Global), Long context (1M), Self-hostable
Best for
Highest open-weight coding performance, 1M context agentic tasks, complex multi-step engineering, long-context reasoning
Works well with
Agent / Orchestration
Conflicts & caveats
- Trae's built-in model menu may not include MiMo V2.5 Pro — Trae primarily ships with Claude/GPT/Gemini/DeepSeek.
- Google Antigravity is built around Gemini 3 Pro; Claude and recent GPT-5 models also work, but MiMo V2.5 Pro is not in the supported model list.
- Kiro's spec mode is tuned for Claude models — MiMo V2.5 Pro may work but spec-driven flows are best with Claude.
- Cursor's built-in model menu may not include MiMo V2.5 Pro — verify it's available in your Cursor model picker.
- OpenAI Codex (VS Code) is tied to OpenAI's GPT-5.1 Codex family — MiMo V2.5 Pro is not selectable inside this integration.
- Gemini CLI is locked to Google Gemini models — your LLM is MiMo V2.5 Pro.
- Privacy conflict: Self-hosted MiMo V2.5 Pro sends code to cloud @codebase (Cursor). Use local context (Continue indexing, ChromaDB, LanceDB, pgvector, Vespa self-hosted) for true privacy.
- Claude Code only works with Claude models — your LLM is MiMo V2.5 Pro.
- Devin uses Cognition's proprietary model internally — your selected MiMo V2.5 Pro will be ignored.
- OpenAI Codex (Cloud) runs GPT-5.1 Codex internally — your selected MiMo V2.5 Pro will be ignored.
- Jules runs Gemini models internally — your selected MiMo V2.5 Pro will be ignored.
- The Claude Code SDK is tuned for Claude models — MiMo V2.5 Pro may work via the model adapter but loses Claude-specific features (thinking, prompt caching, sub-agents).
- Lovable uses a fixed internal model — your selected MiMo V2.5 Pro will be ignored.
- Replit Agent 3 uses its own model selection internally — your selected MiMo V2.5 Pro will be ignored.
Build a full stack around MiMo V2.5 Pro — Flowpicker shows compatibility warnings before you commit.
Open the stack planner →