Xiaomi: MiMo-V2.6-ProActive

xiaomi/mimo-v2.6-pro

MiMo-V2.6-Pro is Xiaomi’s most capable open-source model in the MiMo-V2.6 series, built to scale reinforcement learning on verifiable and complex tasks for stronger reasoning and broader capability growth. It achieves leading open-source performance on the Artificial Analysis Intelligence Index while maintaining the same API pricing as the V2.5 series. The model is designed for users who need top-tier intelligence, strong efficiency, and production-ready cost performance.

By:XiaomiInput Type:Output Type:Publish time:2026-09-22

Providers

Route requests across multiple providers. Copy a provider slug to set your preference.

ProviderCache Hit RateContext

Xiaomi

xiaomi

97.4%$0.435/ M tokens$0.87/ M tokensRead:0.0036/ M tokensWrite:-/ M tokens1.05M3.5s43.4tps

Uptime

24hours

Direct request success rate on AI Gateway and per-provider.

Oct 26, 20:19

Xiaomi100.00%

Throughput

24hours

P50 throughput on live AI Gateway traffic, in tokens per second (TPS).

Oct 26, 19:00

Xiaomi43.4 tps

Latency

24hours

P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds.

Oct 26, 19:00

Xiaomi3.50s

Activity

Token volume and request traffic to this model over time.

Token Consumption

Oct 25

Xiaomi221.4M

Token volume broken down by the provider that served each request. Larger segments indicate providers handling more of this model's traffic.

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows

Metrics sourced fromArtificial Analysis

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for. View All

Token Ranking

Claude CodeClaude Code is Anthropic's agentic coding tool that runs in the terminal, understands a project's codebase, edits files, runs commands, and handles workflows such as tests, debugging and git operations through natural-language instructions. It is also available as IDE extensions (VS Code, JetBrains), a desktop app and a web surface, and is used by developers to build features, fix bugs and automate routine development tasks.

101.8M83.75%

OpenQiao Studio ChatOpenQiao Studio Chat is the built-in web chat workspace of the OpenQiao AI model aggregation platform, operated by OpenQiao Singapore. It lets users converse with many different large language models in a browser GUI, with features such as multi-model side-by-side comparison, multimodal file input, Artifacts generation, web search, image generation/editing and voice input/output.

99.4K65.61%

OpenCodeOpenCode is an open-source, MIT-licensed AI coding agent built by the team behind SST (now Anomaly), available as a terminal TUI/CLI, a desktop app, and IDE extensions. It is model-agnostic and works with many LLM providers or local models, letting developers explore codebases, plan changes, edit files, run shell commands, and use LSP and MCP integrations directly from their workflow.

10.2K

Related Models

More models from Xiaomi

Xiaomi: MiMo-V2.6-Pro-UltraSpeed

396.78Mtokens

MiMo-V2.6-Pro-UltraSpeed is an ultra-fast deployment variant in Xiaomi’s MiMo-V2.6 series, designed for users who need extreme generation speed while maintaining the same output quality. Built on the MiMo-V2.6 family’s native omnimodal capabilities, it is suited for high-throughput generation and complex multimodal reasoning workloads.

Xiaomi: MiMo-V2.6-Flash

9.84Btokens

MiMo-V2.6-Flash is Xiaomi's natively omnimodal foundation model optimized for the best balance of intelligence, efficiency, and cost. It supports long-context reasoning and agentic workflows across coding, visual understanding, automation, and tool use, making it well suited for high-throughput assistants and production applications.

Xiaomi: MiMo-V2.5-ASR

63.68Ktokens

MiMo-V2.5-ASR is an open-source speech recognition model developed by Xiaomi MiMo. It supports bilingual Chinese–English recognition, a wide range of Chinese dialects, code-switching, lyrics transcription, knowledge-intensive content, noisy environments, multi-speaker scenarios, and other challenging acoustic conditions. Through large-scale mid-training, high-quality supervised fine-tuning (SFT), and novel reinforcement learning (RL) algorithms, MiMo-V2.5-ASR achieves state-of-the-art performance across multiple authoritative benchmarks.