Xiaomi's MiMo-V2.5-Pro AI Model Achieves Perfect Score on University Compiler Project in 4.3 Hours
By
Mohit Geryani
The bagel they save for the regulars. Don't skim, savour.
Summary
Xiaomi's MiMo-V2.5-Pro AI model achieved a perfect score (233/233) on Peking University's SysY compiler project — a complex Rust-based compiler build that typically takes students weeks — completing it in just 4.3 hours. The model demonstrates advanced long-horizon coherence, strong agentic capabilities, and sustained performance across thousands of tool calls. Xiaomi has confirmed the V2.5 series will be open-sourced, though V2.5-Pro itself remains closed for now.
Key quotes
· 4 pulledMiMo-V2.5-Pro finished it in 4.3 hours. Perfect score. 233 out of 233 tests passed on a hidden test suite it had never seen.
That's a real university project and a model that scored higher than most students who spent weeks on it.
Xiaomi built this, which is still a sentence that takes a moment to process.
Better long-horizon coherence, stronger agentic capabilities, and the ability to sustain complex tasks across more than a thousand tool calls without losing the thread.
You might also wanna read
Xiaomi Releases MiMo: Open-Source AI Model Series Optimized for Reasoning Tasks
Xiaomi has released MiMo, an open-source large language model series under Apache 2.0 license that is specifically designed for reasoning ta
Xiaomi releases MiMo-V2.5-ASR: open-source 8B speech recognition model supporting Mandarin, English, dialects, and song lyrics
MiMo-V2.5-ASR is an 8-billion-parameter open-source speech recognition model developed by Xiaomi. It supports transcription of Mandarin, Eng
MiniCPM 4.0: Open-source 8B multimodal AI model outperforms GPT-4o and Gemini Pro on vision benchmarks
MiniCPM 4.0 is an ultra-efficient 8B open-source multimodal AI model designed for on-device use that outperforms larger models like GPT-4o a
