Xiaomi: MiMo-V2.5
Analysis Summary
Xiaomi: MiMo-V2.5 is developed by Xiaomi. Released in April 2026, it is one of the newest models we cover. On our leaderboard it earns Professional-tier status, ranking #10 of 565 models in our overall business-suitability ranking. For raw reasoning ability it ranks #24 of 374, putting it in the top quartile for overall intelligence.
For engineering teams, Xiaomi: MiMo-V2.5 is a standout coder, ranking #34 of 311 on our coding index for code generation, refactoring, and debugging. It also ranks #26 of 286 for agentic, multi-step tasks ā the autonomous, tool-driven workflows that underpin business automation. Its 1M-token context window is larger than 97% of the models we list, suiting long documents, large codebases, and retrieval-heavy workloads. Crucially for business adoption, Xiaomi: MiMo-V2.5 combines tool use, function calling, and vision input in a single model, letting teams consolidate several use cases instead of stitching together multiple services.
At $0.140 input and $0.280 output per 1M tokens, Xiaomi: MiMo-V2.5 is aggressively priced for high-volume use which makes it easy to justify for cost-sensitive, high-throughput deployments. Xiaomi: MiMo-V2.5 is a dependable pick for businesses that need strong, well-rounded performance without paying frontier prices.
Editorial notes
MiMo-V2.5 from Xiaomi reaches an intelligence index of 49 with world-class coding (42.1), strong agentic performance (66.2), multimodal input including audio and video, a 1M token context, and aggressive pricing at $0.14/$0.28 per million tokens.
Assessed May 31, 2026
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Xiaomi: MiMo-V2.5 compares
Xiaomi: MiMo-V2.5 ranks #24 of 374 AI models we track for overall intelligence, #34 of 311 for coding, #26 of 286 for agentic tasks. Its 1M-token context window is larger than 97% of the models we list. At $0.14 per million input tokens it is cheaper than 58% of comparable models.
About Xiaomi: MiMo-V2.5
MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Xiaomi: MiMo-V2.5 stack up?
Compare side-by-side with other professional models.
Model Information
| OpenRouter ID |
xiaomi/mimo-v2.5
|
| Provider | xiaomi |
| Release Date | April 22, 2026 |
| Context Length | 1,048,576 tokens |
| Max Completion | 131,072 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.14 | $0.000140 |
| Output | $0.28 | $0.000280 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about Xiaomi: MiMo-V2.5
How much does Xiaomi: MiMo-V2.5 cost?
Xiaomi: MiMo-V2.5 costs $0.14 per million input tokens and $0.28 per million output tokens.
What is the context window of Xiaomi: MiMo-V2.5?
Xiaomi: MiMo-V2.5 has a context window of 1,048,576 tokens (1M).
Is Xiaomi: MiMo-V2.5 good for coding?
On our coding benchmark index, Xiaomi: MiMo-V2.5 ranks #34 of 311 models, placing it in the top quartile of the field for code generation and debugging.
What can Xiaomi: MiMo-V2.5 do?
Xiaomi: MiMo-V2.5 supports image/vision input, tool use, and function calling.
Who created Xiaomi: MiMo-V2.5?
Xiaomi: MiMo-V2.5 is developed by Xiaomi and was released on April 22, 2026.
