Kimi K2 Thinking vs. DeepSeek V3.1 (Reasoning)

Name: Intelligence
Creator: Artificial Analysis
License: https://artificialanalysis.ai/docs/legal/Terms-of-Use.pdf

Comparison between Kimi K2 Thinking and DeepSeek V3.1 (Reasoning) across intelligence, price, speed, context window and more.

For details relating to our methodology, see our Methodology page.

	Kimi	DeepSeek
Intelligence
Intelligence Index	22*	13*
Humanity's Last Exam	24%	14%
CritPt	3%	2%
AA-Omniscience	−21	−30
AA-LCR v1.1	72%	57%
Cost
Price per 1M Tokens	$0.79	$0.69
Input Price per 1M Tokens	$0.60	$0.58
Output Price per 1M Tokens	$2.50	$1.68
Cache Hit Price per 1M Tokens	$0.60	$0.58
Token Use
Performance
Output Speed	123 tokens/s	121 tokens/s
Time to First Token	1.55s	2.79s
Time to First Answer Token	17.79s	19.35s
End-to-End Response Time	21.85s	23.49s
Technical specifications
Context Window	256k tokens~384 A4 pages of size 12 Arial font	128k tokens~192 A4 pages of size 12 Arial font
Release Date	November 2025	August 2025
Total parameters	1T	685B
Active parameters	32B	37B
Reasoning	Yes	Yes
Input modality	Supports: text	Supports: text
Output modality	Supports: text	Supports: text
Open Source (Weights)	Yes	Yes
License	Modified MIT License	MIT
License Supports Commercial Use Without Restrictions	Yes	Yes

* Estimated

Intelligence

Artificial Analysis Intelligence Index · Higher is better

Speed

Output tokens per second · Higher is better

Cost per Task

Weighted average cost (USD) per Intelligence Index task · Lower is better

No data available

Intelligence

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

Estimate (independent evaluation forthcoming)

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.

Artificial Analysis Intelligence Index by Open Weights / Proprietary

Estimate (independent evaluation forthcoming)

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.

Intelligence Index vs. Cost per Task

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

Most attractive quadrant

Pareto line

AA-Briefcase v1.1

GDPval-AA v2.1

Cost per Task (USD, Log Scale)

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.

Benchmarks

Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better

AA-Briefcase v1.1Updated

Agentic knowledge work, (Elo-500)/2000

AA-Omniscience Accuracy

Knowledge

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

AutomationBench-AA

Agentic SaaS workflows

GDPval-AA v2.1Updated

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

Humanity's Last Exam

Reasoning & knowledge

GDP.pdf

Professional document reasoning, All-pass

Terminal-Bench 4.0

Agentic coding & terminal use

AA-LCR v1.1

Long context reasoning

SciCodeUnder review

Coding

CritPt

Physics reasoning

Terminal-Bench-Science 0.1New

Agentic scientific research workflows in a terminal

FrontierCode 1.1New

Agentic software engineering in open-source repositories

AA-AnalystAgent

Quantitative analysis on spreadsheets & documents

Harvey LAB-AA v1.1Updated

Legal agentic work, Hallucination-Gated All-Pass Rate

EnterpriseOps-Gym-AA

Agentic business operations

AA-3DNew

Agentic interactive 3D experiences, (Elo-500)/2000

ITBench-AA

Kubernetes incident root-cause analysis

MLCR-AAUpdated

Medical long context reasoning

MMMU-Pro

Visual reasoning

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

AA-Omniscience

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.

Openness Index

Artificial Analysis Openness Index: Score

Openness Index assesses model openness on a 0 to 100 normalized scale (higher is more open)

Intelligence Index Comparisons

Intelligence Index vs. Cost per Task

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

Most attractive quadrant

Pareto line

AA-Briefcase v1.1

GDPval-AA v2.1

Cost per Task (USD, Log Scale)

Cost

Cost per Intelligence Index Task

Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better

Cost to Run Artificial Analysis Intelligence Index

Cost (USD) to run all evaluations in the 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).

Pricing: Cache Hit, Input, and Output

Price (USD per M Tokens)

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.

Context Window

Context window: tokens limit · Higher is better

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

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

Speed

Measured by Output Speed (tokens per second)

Output Speed

Output tokens per second · Higher is better

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).

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

Time per Intelligence Index Task

Weighted average decode time (minutes) per Intelligence Index task · Excludes TTFT and overhead time · Lower is better

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.

Latency

Measured by Time (seconds) to First Token

Latency: Time To First Answer Token

Seconds to first answer token received · Accounts for reasoning model 'thinking' time

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.

End-to-End Response Time

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

End-to-End Response Time

Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better

Seconds to receive a 500 token response. Key components:

Input time: Time to receive the first response token
Thinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).
Answer time: Time to generate 500 output tokens, based on output speed

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

Model Size (Open Weights Models Only)

Model Size: Total and Active Parameters

Comparison between total model parameters and parameters active during inference (billions)

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.

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.

Frequently Asked Questions

Kimi K2 Thinking is more intelligent. Kimi K2 Thinking scores 22 (estimated), compared with DeepSeek V3.1 (Reasoning) at 13 (estimated) on the Artificial Analysis Intelligence Index.

Kimi K2 Thinking is faster. Kimi K2 Thinking generates 123.2 tokens per second, compared with DeepSeek V3.1 (Reasoning) at 120.8 tokens per second.

DeepSeek V3.1 (Reasoning) is cheaper. DeepSeek V3.1 (Reasoning) costs $0.69 per 1M tokens, compared with Kimi K2 Thinking at $0.79 per 1M tokens (7:2:1 cache hit/input/output ratio).

Kimi K2 Thinking has lower latency. Kimi K2 Thinking has a time to first token of 1.55s, compared with DeepSeek V3.1 (Reasoning) at 2.79s.

Kimi K2 Thinking has a larger context window. Kimi K2 Thinking supports 260k tokens, compared with DeepSeek V3.1 (Reasoning) at 130k tokens.

Kimi K2 Thinking vs. DeepSeek V3.1 (Reasoning)

Intelligence

Speed

Cost per Task

Intelligence

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index by Open Weights / Proprietary

Artificial Analysis Intelligence Index

Open Weights

Intelligence Index vs. Cost per Task

Cost per Intelligence Index Task

Artificial Analysis Intelligence Index

Benchmarks

Evaluations

Intelligence Evaluation Relevance

Artificial Analysis Intelligence Index

AA-Omniscience

AA-Omniscience Index

AA-Omniscience Index

Openness Index

Artificial Analysis Openness Index: Score

Intelligence Index Comparisons

Intelligence Index vs. Cost per Task

Cost per Intelligence Index Task

Artificial Analysis Intelligence Index

Cost

Cost per Intelligence Index Task

Cost per Intelligence Index Task

Cost to Run Artificial Analysis Intelligence Index

Cost to Run Artificial Analysis Intelligence Index

Pricing: Cache Hit, Input, and Output

Cache Hit

Context Window

Context Window

Context Window for RAG

Context Window

Speed

Output Speed

Output Speed

Model Performance Representation

Time per Intelligence Index Task

Time per Intelligence Index Task

Latency

Latency: Time To First Answer Token

Time to First Answer Token

End-to-End Response Time

End-to-End Response Time

End-to-End Response Time

Model Performance Representation

Model Size (Open Weights Models Only)

Model Size: Total and Active Parameters

Total Parameters

Active Parameters at Inference Time

Frequently Asked Questions

Which is more intelligent, Kimi K2 Thinking or DeepSeek V3.1 (Reasoning)?

Which is faster, Kimi K2 Thinking or DeepSeek V3.1 (Reasoning)?

Which is cheaper, Kimi K2 Thinking or DeepSeek V3.1 (Reasoning)?

Which has lower latency, Kimi K2 Thinking or DeepSeek V3.1 (Reasoning)?

Which has a larger context window, Kimi K2 Thinking or DeepSeek V3.1 (Reasoning)?