Skip to main content
AITier

Kimi K2.5 (Non-reasoning)

KimiKimiOpen WeightMIT · Commercial OK

Description

Kimi K2.5 is Moonshot AI's flagship agentic model and a new SOTA open model. It unifies vision and text, thinking and non-thinking modes, and single-agent and multi-agent execution into one model. Built with Full-Parameter RL tuning, it achieves state-of-the-art performance across agents, coding, image, and video benchmarks.

Release Date
2026-01-27
Parameters
1.0T
Context Length
262K
Modalities
image, text, video

Capability Radar

26
general
40
coding
79
reasoning
52
science
50
agents
80
multimodal

Rankings

Domain#RankScoreSource
Agentic Capability126
34.0
LS
Code Ranking196
54.0
AA
General Ranking200
55.0
AA
Multimodal Ranking26
57.0
LS
Science184
56.0
AA

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Agents

WideSearch79.0%SR
DeepSearchQA77.1%SR
BrowseCompOpenAI (2025)74.9%SR
PaperBench63.5%SR
Terminal-Bench 2.0Stanford × Laude Institute (2026)50.8%SR
SWE-Bench ProPrinceton NLP (2024)50.7%SR
CyberGym41.3%SR
FrontierSWE26.0%

Biology

GPQANYU + Cohere + Anthropic (2023)87.6%SR
SciCode48.7%SR

Code

SWE-Bench Verified76.8%SR
SWE-bench Multilingual73.0%SR
OJBench (C++)57.4%SR

Economics

FinSearchComp T2&T367.8%SR

Finance

MMLU-Pro87.1%SR

General

LiveCodeBench v685.0%SR
MMMU-Pro78.5%SR
SimpleVQA0.71 / 100SR
LiveBench69.1%
LongBench v261.0%SR

Healthcare

VideoMMMU86.6%SR

Image To Text

OCRBench92.3%SR

Long Context

LongVideoBench79.8%SR
LVBench75.9%SR
AA-LCR70.0%SR

Math

AIME 202596.1%SR
HMMT 202595.4%SR
MathVista-Mini90.1%SR
MathVision84.2%SR
IMO-AnswerBench81.8%SR
Humanity's Last Exam50.2%SR

Multimodal

InfoVQAtest92.6%SR
OmniDocBench 1.588.8%SR
Video-MME87.4%SR
MMVU80.4%SR
CharXiv-R77.5%SR
MotionBench70.4%SR
WorldVQA46.3%SR
ZEROBench0.11 / 100SR

Reasoning

Seal-057.4%SR

AA Evaluation Indices

(Artificial Analysis)
Intelligence Index(Artificial Analysis)
30.1
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.8
Gpqa(NYU + Cohere + Anthropic (2023))
0.8
Lcr(Artificial Analysis)
0.7
Ifbench(Google Research (2023))
0.4
Scicode(UIUC + Argonne National Lab (2024))
0.4
Terminalbench Hard(Stanford × Laude Institute (2026))
0.2
Hle(Center for AI Safety + Scale AI (2025))
0.1

LLM Stats Category Scores

(LLM Stats (zeroeval))
Language
90
Legal
90
Finance
90
Image To Text
80
Long Context
80
Math
80
Frontend Development
80
Video
80
Multimodal
70
Physics
70
Reasoning
70
Search
70
Structured Output
70
General
70
Healthcare
70
Biology
70
Chemistry
70
Vision
70
Agents
60
Code
50
Tool Calling
50
Safety
40

Pricing

Input Price$0.6 / 1M tokens
Output Price$3 / 1M tokens
Blended Price (3:1)$1.2 / 1M tokens
Cache Read Price$0.095 / 1M tokens

Speed

Tokens/sec0.0
Time to First Token0.00s
Time to Answer0.00s

Provider Price Ranking

Provider Price Ranking

1 providers

ProviderInputOutput
1KimiPRIMARY
$0.6
$3

Compare pricing across different API providers for this model.

External Sources

LLM StatsArtificial Analysis