MiMo-V2.6-Pro

Proprietarygeneralreasoningcodingagent

Leaderboard Score

56.5

Scale: 0 - 100

Throughput Speed

55 tps

Context Window

API Pricing / 1M

$0.44

Parameter Scale

Proprietary

Verified AI Radar & Benchmarks•8 Evaluated Metrics

Capability Radar & Benchmark Scores

Multi-Axis Capability Radar

Comparing MiMo-V2.6-Pro against Frontier Top 10 & Open-Source average

0 - 100 Scale

MiMo-V2.6-Pro

Frontier Top 10 Avg

Open-Source Avg

Performance Vectors

Where MiMo-V2.6-Pro Leads

Coding & SWETop 10: 79.1% • OS: 47.6%

78.4%-0.7% vs Top 10

Reasoning & MathTop 10: 74.6% • OS: 46.6%

65.2%-9.4% vs Top 10

Agent & Tool AutomationTop 10: 71.2% • OS: 31.9%

42.5%-28.7% vs Top 10

Terminal & CLI ExecutionTop 10: 80.4% • OS: 47.6%

76.2%-4.2% vs Top 10

MMLU & Knowledge QATop 10: 50% • OS: 86.7%

70.6%+20.6% vs Top 10

Cyber & Security ExploitsTop 10: 87.8% • OS: 80.6%

53.7%-34.1% vs Top 10

All Verified Benchmark Evaluations

Direct Pass@1 and resolution rates across standardized evaluations.

CodingReasoningAgenticMath

Featured Compute Platform

Run Benchmarks on Dedicated AI Clusters

Zero-cold-start inference endpoints with dedicated GPU instances.

Compare With Alternatives →

Executive Analysis & Verdict

MiMo-V2.6-Pro by Xiaomi is a top-tier frontier multimodal model ranking #11 globally with a 56.5 overall score, 78.4% on SWE-bench Verified, 1,745 Arena Elo, and 49.2 on the Artificial Analysis Intelligence Index at $0.44/1M.

Key Strengths & Highlights

•World-class cost-to-intelligence ratio: 78.4% SWE-bench Verified and 65.2% GPQA Diamond at just $0.44/1M
•1,745 LMSYS Arena Elo and 1,585 AA-Briefcase Elo rivaling western flagships
•Full 1M token context window with native multimodal vision, document analysis, and tool orchestration

Limitations & Considerations

•Throughput is balanced (55 tps) rather than ultra-fast

Recommended Workflows

Cost-effective agentic coding, complex autonomous workflows, high-difficulty reasoning, and 1M multimodal document processing

Xiaomi’s Flagship Multimodal Frontier Model

Xiaomi’s MiMo-V2.6-Pro represents a major leap in open multimodal reasoning and agent capabilities. Benchmarked at 1,745 Arena Elo, 78.4% SWE-bench Verified, and 49.2 on the Artificial Analysis Intelligence Index, it secures a top-tier global rank (#11) while maintaining disruptive pricing ($0.44 / 1M tokens).

Key Specifications

Provider: Xiaomi
License / Weights: Proprietary
Context Window: 1,048,576 tokens (1M)
Max Output: 131,072 tokens
Inference Speed: 55 tps
API Pricing: $0.44 / 1M input tokens ($0.87 / 1M output tokens, $0.0036 cache read)

Benchmark Highlights

Overall Score: 56.5 / 100 (Global Rank #11)
SWE-bench Verified: 78.4%
GPQA Diamond: 65.2%
MATH-500: 74.5%
Terminal-Bench: 76.2%
LMSYS Arena Elo: 1,745
AA-Briefcase Elo: 1,585
Artificial Analysis Intelligence Index: 49.2

Frequently Asked Questions About MiMo-V2.6-Pro

What is MiMo-V2.6-Pro and who developed it?↓

MiMo-V2.6-Pro is a proprietary large language model developed by Xiaomi. It ranks #11 on the RankLLMs composite leaderboard, ahead of 88% of the 85 models we track, with an overall score of 56.5 / 100.

What context window and inference speed does MiMo-V2.6-Pro offer?↓

MiMo-V2.6-Pro supports a NaNK-token input context window and generates about 55 tps tokens per second in our reference measurements and suitable for extended reasoning sessions and multi-turn agent workflows..

Why is MiMo-V2.6-Pro priced so far below its peers?↓

MiMo-V2.6-Pro is cheaper than 68% of the priced models we track at $0.44 per 1M tokens, while keeping competitive benchmark scores - which is why it rates well on cost per solved task, not just per token.

What is MiMo-V2.6-Pro best at?↓

MiMo-V2.6-Pro is strongest in World-class cost-to-intelligence ratio: 78.4% SWE-bench Verified and 65.2% GPQA Diamond at just $0.44/1M; 1,745 LMSYS Arena Elo and 1,585 AA-Briefcase Elo rivaling western flagships; Full 1M token context window with native multimodal vision, document analysis, and tool orchestration. Full pillar-by-pillar numbers are in the benchmark tables above.

What should you watch out for with MiMo-V2.6-Pro?↓

Known trade-offs include: Throughput is balanced (55 tps) rather than ultra-fast. Weigh these against the strengths above for your specific workload.