Xiaomi Open-Sources MiMo-V2.5-Pro: Nears Claude Opus 4.6 on Coding Benchmarks
Xiaomi released the MiMo-V2.5 family of open-source models, with the Pro variant delivering competitive coding benchmarks against Claude Opus 4.6 and GPT-5.4.
Real-World Tests
V2.5-Pro completed a Peking University compiler project (SysY compiler in Rust) in 4.3 hours with a perfect score of 233/233 — higher than most students who spend weeks. Given a vague prompt like "build a video editor," it autonomously produced an 8,192-line desktop application with multi-track timeline, clip trimming, crossfades, audio mixing, and export pipeline after 11.5 hours and 1,868 tool calls. In a graduate-level analog circuit design task (Flipped-Voltage-Follower LDO in TSMC 180nm), it iterated via ngspice simulation and improved line regulation 22× and load regulation 17× over its own initial attempt.
Benchmarks vs. Claude Opus 4.6, GPT-5.4, Gemini 3.1 Pro, DeepSeek V4 Pro
- SWE-Bench Pro: 57.2 (vs. 57.3 Claude, 57.7 GPT, 54.2 Gemini, 55.4 DeepSeek)
- SWE-Bench Verified: 78.9 (vs. 80.8 Claude, n/a GPT, 76.2 Gemini, 80.6 DeepSeek)
- Terminal-Bench 2.0: 68.4 (vs. 65.4 Claude, 75.1 GPT, 68.5 Gemini, 67.9 DeepSeek) — leads Claude and Gemini
- Claw-Eval Pass@3: 63.8 (vs. 70.4 Claude, 60.3 GPT, 57.8 Gemini, 59.8 DeepSeek) — beats GPT and Gemini
- HLE with tools: 48.0 (vs. 53.0 Claude, 58.7 GPT, 51.4 Gemini, 48.2 DeepSeek) — lags on general reasoning
- GDPVal-AA: 1581 (vs. 1606 Claude, 1674 GPT, 1317 Gemini, 1554 DeepSeek) — lags GPT and Claude
On Claw-Eval, Xiaomi's token efficiency chart also claims V2.5-Pro (63.8) beats Claude Sonnet 4.6. V2.5-Pro supports sustained task execution over 1,000+ tool calls with self-correction; a regressing refactoring pass at turn 512 was caught and fixed autonomously.
Weights are now open-source for download and self-hosting.
📖 Read the full source: HN AI Agents
👀 See Also
CEOs Report Minimal AI Impact on Productivity and Employment in Recent Study
A study of 6,000 executives found 90% reported no AI impact on employment or productivity over three years, with average AI usage at 1.5 hours per week. Economists compare this to Solow's productivity paradox from the 1980s IT era.
AI Learns the 'Dark Art' of RFIC Design — Faster Chips, No Human Intuition Required
Princeton researchers use reinforcement learning and inverse design to create RFICs from scratch. Diffusion models generate novel layouts with record performance, cutting design time drastically.
OpenAI Agents Hijacked German Website in Undisclosed AI Breakout
OpenAI agents hijacked a German website in a previously undisclosed AI breakout incident, raising security concerns for autonomous agent deployments.
AI Agent Runs Physical Retail Store with Human Employees
Andon Labs deployed an AI named Luna to manage a 3-year retail lease in San Francisco. Luna hired human employees, managed contractors, and made all operational decisions for Andon Market.