MiMo-V2.5-Pro

Released
2026-04-22
Last refreshed
2026-10-29
Status
Researched 21d ago
ProprietaryCommercial use: restrictedCodingRAGAgentsLong contextClassificationJSON / Tool useCodingAgentLong Context
Xiaomi releases · 10 in the last 12 months · this family litChangelog →
Specifications
Family
MiMo
Released
2026-04-22
Context
1M
Parameters
1T
Architecture
Mixture of Experts
Specialization
code
Openness
Proprietary
License
ProprietaryRestricted
Weights
Not released
Code
Unknown
Training
Pretrained
Created by

Consumer electronics and AI research.

Beijing, China
Founded 2010
Website
Pricing
Output / 1M
$0.870
Input / 1M
$0.435

Cheapest of 3 routes · Xiaomi · cache read $0.0036

About

Xiaomi's April 22, 2026 public-beta flagship in the MiMo-V2.5 series. The official Xiaomi MiMo page describes MiMo-V2.5-Pro as its most capable model to date, focused on general agentic capability, complex software engineering, long-horizon tasks, and ultra-long-context instruction following. OpenRouter lists it as text-to-text with 1,048,576 token context, 131,072 max completion tokens, reasoning controls, tool use, and response_format support. Xiaomi says the V2.5 series will be open-sourced soon, but no public weights/license were verified at research time.

Top use-case fit: coding, agents, and build tasks

Coding

Q/$ C

Agents

Q/$ B

Providers(3)

Compare all 3

Compare API pricing across 3 tracked provider routes for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MCacheRoute
Xiaomi$0.435$0.870read $0.0036
Serverless
OpenRouter$0.435$0.870read $0.0036
Serverless
Novita AI$2.00$6.00read $0.400
Serverless

Capabilities

JSON / Tool useStructured Outputs

Benchmark peer barsfor Coding

Benchmark scores(9)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
89.4—Observed 2026-04-28—
68.5—Observed 2026-04-28—
66.7diamondObserved 2026-04-28—
78.9SWE-Bench Verified (Resolved)Observed 2026-04-28—
57.2SWE-bench Pro (resolved%)Observed 2026-06-07—
68.4Terminal-Bench 2.0 (score)Observed 2026-06-07—
2.0xhighObserved 2026-06-30—
1466.0text_style_control overall 2026-10-22 (style control, default view)Observed 2026-10-26
Configuration: MiMo-V2.5-Pro
Harness: LMArena blind pairwise human votes, Bradley-Terry
Evaluator: LMArena
Confidence: confirmed
Notes: LMArena text style control leaderboard, overall category, published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @9761a3ce, latest split). Board entry 'MiMo-V2.5-Pro': rank 51, Arena Score 1466.5 (95% CI 1463.0-1470.0), 77883 votes. Retrieved 2026-10-26.
Source

Source: LMArena (lmarena.ai), CC BY 4.0

1438.0text creative_writing 2026-10-22Observed 2026-10-22
Configuration: MiMo-V2.5-Pro
Harness: LMArena blind pairwise human votes, Bradley-Terry
Evaluator: LMArena
Confidence: confirmed
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'MiMo-V2.5-Pro' (category creative_writing in text/latest-00000-of-00001.parquet): rank 50 of 416, rating 1438.0 (95% CI 1431.9-1444.1), 14635 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Source

Source: LMArena (lmarena.ai), CC BY 4.0

Migration checks

No linked migration route is available for this model yet.

API versions

mimo-v2.5-proXiaomi MiMo-V2.5-Pro

Compare MiMo-V2.5-Pro with other models

Show all 52 popular comparisonssorted by 7-day search impressions
MiMo-V2.5-Pro vs Claude 3.7 Sonnet34MiMo-V2.5-Pro vs Llama Guard 2 8B32MiMo-V2.5-Pro vs Qwen3.5-9B30MiMo-V2.5-Pro vs Claude Haiku 4.530MiMo-V2.5-Pro vs Gemma 7B Instruct27MiMo-V2.5-Pro vs GPT-126MiMo-V2.5-Pro vs Mistral Small 322MiMo-V2.5-Pro vs Mistral 7B v0.121MiMo-V2.5-Pro vs GPT-420MiMo-V2.5-Pro vs Gemini 3.1 Pro Preview Custom Tools20MiMo-V2.5-Pro vs Nemotron Mini 4B Instruct19MiMo-V2.5-Pro vs Llama Guard 7B18MiMo-V2.5-Pro vs ShieldGemma 9B17MiMo-V2.5-Pro vs GPT-2 Medium15MiMo-V2.5-Pro vs Claude Instant 1.115MiMo-V2.5-Pro vs Mistral Nemotron13MiMo-V2.5-Pro vs GPT-212MiMo-V2.5-Pro vs Phi-4 Mini Flash Reasoning12MiMo-V2.5-Pro vs Llama 3.3 Nemotron Super 49B v112MiMo-V2.5-Pro vs Mistral Large 3 675B Instruct11MiMo-V2.5-Pro vs Mistral Medium 310MiMo-V2.5-Pro vs Together AI - Llama 3 8B Lite9MiMo-V2.5-Pro vs Sarvam-M Multilingual Hybrid9MiMo-V2.5-Pro vs Dracarys Llama 3.1 70B Instruct7MiMo-V2.5-Pro vs Llama 3.1 Nemotron Nano VL 8B v17MiMo-V2.5-Pro vs Magistral Small 25067MiMo-V2.5-Pro vs Together AI Qwen2-7B-Instruct7MiMo-V2.5-Pro vs Bielik 11B v2.6 Instruct6MiMo-V2.5-Pro vs Nemotron Mini Hindi 4B Instruct6MiMo-V2.5-Pro vs Phi-4 Reasoning Vision 15B5MiMo-V2.5-Pro vs Llama 3 Swallow 70B Instruct5MiMo-V2.5-Pro vs Llama 3.1 NemoGuard 8B Topic Control4MiMo-V2.5-Pro vs Qwen2-7B-Instruct4MiMo-V2.5-Pro vs Together AI Qwen2-72B-Instruct4MiMo-V2.5-Pro vs Llama 3.1 Nemotron Nano 4B v1.14MiMo-V2.5-Pro vs Llama 3.1 Nemotron 70B Reward4MiMo-V2.5-Pro vs Falcon 3 7B Instruct3MiMo-V2.5-Pro vs Llama 3.1 Swallow 8B Instruct3MiMo-V2.5-Pro vs Teuken 7B Instruct3MiMo-V2.5-Pro vs Colosseum 355B Instruct2MiMo-V2.5-Pro vs GPT-4 Turbo Preview2MiMo-V2.5-Pro vs Llama 3.1 NemoGuard 8B Content Safety2MiMo-V2.5-Pro vs Seed-OSS 36B Instruct2MiMo-V2.5-Pro vs Mistral Large 2 (2407)2MiMo-V2.5-Pro vs Sarvam 30B2MiMo-V2.5-Pro vs Aquila 2 34B2MiMo-V2.5-Pro vs Llama 3 Taiwan 70B Instruct1MiMo-V2.5-Pro vs text-davinci1MiMo-V2.5-Pro vs Marin 8B Instruct1MiMo-V2.5-Pro vs Aquila 2 7B1MiMo-V2.5-Pro vs Stockmark 2 100B Instruct1MiMo-V2.5-Pro vs Italia 10B Instruct1