MiMo-v2.6-Pro: Intelligence, Performance and Price Analysis

以下正文同步自 Hacker News，版权归原站所有，已转换为易读排版。

Artificial AnalysisK

Artificial AnalysisModels

Coding Agents

Image, Speech, Video

Inference

Leaderboards

About

AI Trends

Arenas

K

Xiaomi

•Open weights model

CompareTry it out API Provider Benchmarks

Model summary

IntelligenceUpdated

#1 / 114

46

Artificial Analysis Intelligence Index

4 out of 4 units for Intelligence.

Speed

#12 / 114

124.5

Output tokens per second

4 out of 4 units for Speed.

Cost

#12 / 114

In $0.435Out $0.87Cache Discount 99%

$0.13

Cost per Intelligence Index task

2 out of 4 units for Cost.

Verbosity

#18 / 114

140M

Output tokens from Intelligence Index

3 out of 4 units for Verbosity.

Comparison Summary

MiMo-V2.6-Pro is amongst the leading models in intelligence and reasonably priced when comparing to other open weight models of similar size. It's also notably fast, however somewhat verbose. The model supports text, image, speech, and video input, outputs text, and has a 1M tokens context window.

MiMo-V2.6-Pro scores 46 on the Artificial Analysis Intelligence Index, placing it well above average among comparable models (median: 18). When evaluating the Intelligence Index, it generated 140M tokens, which is somewhat verbose in comparison to the median of 140M.

Pricing for MiMo-V2.6-Pro is $0.43 per 1M input tokens (somewhat expensive, median: $0.30) and $0.87 per 1M output tokens (moderately priced, median: $1.13). In total, it cost $206.66 to evaluate MiMo-V2.6-Pro on the Intelligence Index.

At 125 tokens per second, MiMo-V2.6-Pro is notably fast (75).

ReasoningYesThis page shows the reasoning version of this model.

Input modality

Supports: text, image, speech, and video

Context window1M~1500 A4 pages of size 12 Arial font

Total parameters1.0TActive parameters42BNumber of parameters active per token during inference

LicenseMITModel weightsHugging Face

114 models in this class

Metrics are compared against models of the same class:

IntelligenceUpdated

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.3.2 incorporates 10 evaluations: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1

28 of 656 models

Add model from specific provider

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.3.2 includes: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

28 of 656 models

Add model from specific provider

ProprietaryOpen WeightsOpen Weights (Commercial Use Restricted)

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.3.2 includes: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Open Weights

Indicates whether the model weights are available. Models are labelled as 'Commercial Use Restricted' if commercial use is limited by conditions, and as 'Non-commercial' if the license prohibits commercial use.

Measures the performance of models on specific capabilities and industries

Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better

28 of 153 models

Add model from specific provider

Benchmarks

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better

CodingAgenticTool UsePrivate DatasetUser InteractionFinanceMedicalLegalIntelligence IndexLong ContextMultimodalInstruction FollowingFaithfulnessWritingBusinessSee more

18 of 26 evaluations28 of 656 models

Add model from specific provider

AA-Briefcase v1.1Updated

Agentic knowledge work, (Elo-500)/2000

GDPval-AA v2.1Updated

Agentic real-world work tasks, (Elo-500)/2000

AutomationBench-AAUpdated

Agentic SaaS workflows

Terminal-Bench 4.0New

Agentic coding & terminal use

Humanity's Last Exam

Reasoning & knowledge

GDP.pdfNew

Professional document reasoning, All-pass

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

Harvey LAB-AA

Legal agentic work, criterion pass rate

EnterpriseOps-Gym-AA

Agentic business operations

AA-AnalystAgent

Quantitative analysis on spreadsheets & documents

ITBench-AA

Kubernetes incident root-cause analysis

MLCR-AANew

Medical long context reasoning

Intelligence Evaluation Relevance

While model intelligence generally translates across use cases, specific evaluations may be more relevant for certain use cases.

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.3.2 includes: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

28 of 174 models

Add model from specific provider

AA-Briefcase Elo

AA-Briefcase Elo is a combined metric that aggregates analytical quality Elo, presentation Elo, and rubric pass rate, with rubric performance converted into Elo via synthetic head-to-head matches. Elo and 95% confidence interval bounds are clamped at 0.

28 of 531 models

Add model from specific provider

AA-Omniscience Index

AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct.

19 of 322 models

Add model from specific provider

Intelligence Index Comparisons

Intelligence Index vs. Cost per TaskIntelligence Index vs. Time per TaskIntelligence Index vs. Output SpeedIntelligence Index vs. End-to-End Response Time

Intelligence Index vs. Cost per Intelligence Index Task

Artificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task

28 of 656 models

Most attractive quadrant

Pareto line

XiaomiOpenAIAnthropicSpaceXAIGoogleMetaZ AIDeepSeekKimiAlibabaMiniMaxTencentThinking MachinesNVIDIA

Cost per Intelligence Index Task

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.3.2 includes: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

28 of 656 models

AnswerReasoning

Output Tokens per Intelligence Index Task

The number of tokens required per Intelligence Index task. This is calculated by multiplying the output tokens per eval by the relative weights of each benchmark in the Intelligence Index, then dividing by task count (excluding repeats).

28 of 656 models

AnswerReasoningCache WriteCache HitInput

Cost per Intelligence Index Task

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

28 of 656 models

Add model from specific provider

OutputReasoningCache WriteCache ReadNon-Cache Input

Cost to Run Artificial Analysis Intelligence Index

The cost to run the evaluations in the Artificial Analysis Intelligence Index, calculated using the model's input, cache hit, cache write, reasoning, and answer token prices and the number of tokens used across evaluations (excluding repeats).

28 of 656 models

Add model from specific provider

Cache HitInputOutput

Cache Hit

Price per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail.

4 more notes

Context Window

Context WindowIntelligence Index vs. Context Window

Context Window

Context window: tokens limit · Higher is better

28 of 656 models

Add model from specific provider

Context Window for RAG

Larger context windows are relevant to RAG (Retrieval Augmented Generation) LLM workflows which typically involve reasoning and information retrieval of large amounts of data.

Context Window

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

Measured by Output Speed (tokens per second)

28 of 656 models

Add model from specific provider

Output Speed

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Model Performance Representation

Figures represent performance of the model's first-party API or the median across providers where a first-party API is not available.

28 of 656 models

Time per Intelligence Index Task

The weighted average time (seconds) per Artificial Analysis Intelligence Index task. This is calculated by dividing output tokens per task by output speed, weighted by the relative weights of each benchmark in the Intelligence Index.

Measured by Time (seconds) to First Token

28 of 656 models

Add model from specific provider

Thinking (reasoning models, when applicable)Input processing

Time to First Answer Token

Time to first answer token received, in seconds, after API request sent. For reasoning models, this includes the 'thinking' time of the model before providing an answer. For models which do not support streaming, this represents time to receive the completion.

Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed

28 of 656 models

Add model from specific provider

Outputting time'Thinking' time (reasoning models)Input processing time

End-to-End Response Time

Seconds to receive a 500 token response. Key components:

Model Performance Representation

Figures represent performance of the model's first-party API or the median across providers where a first-party API is not available.

28 of 656 models

Add model from specific provider

Active ParametersPassive Parameters

Total Parameters

The total number of trainable weights and biases in the model, expressed in billions. These parameters are learned during training and determine the model's ability to process and generate responses.

Active Parameters at Inference Time

The number of parameters actually executed during each inference forward pass, expressed in billions. For Mixture of Experts (MoE) models, a routing mechanism selects a subset of experts per token, resulting in fewer active than total parameters. Dense models use all parameters, so active equals total.

MiMo-V2.6-Pro was released on September 21, 2026.

MiMo-V2.6-Pro scores 46 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 18).

MiMo-V2.6-Pro generates output at 124.5 tokens per second (based on Xiaomi's API), which is well above average compared to other open weight models of similar size (median: 74.8 t/s).

MiMo-V2.6

正文由 FLUX 从来源站点 RSS 同步，内容未经改写；遇到排版缺失或需要图片、视频时请以原文为准。