Kimi K2.5 (Non-reasoning)
KimiKimiOpen WeightMIT · Usage Commercial
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.
Date de sortie
2026-01-27
Paramètres
1.0T
Longueur du contexte
262K
Modalités
image, text, video
Radar de capacités
26
general
40
coding
79
reasoning
52
science
50
agents
80
multimodal
Classements
| Domaine | #Rang | Score | Source |
|---|---|---|---|
| Capacité agentique | 130 | 33.0 | LS |
| Classement codage | 205 | 54.0 | AA |
| Classement général | 208 | 55.0 | AA |
| Classement multimodal | 27 | 57.0 | LS |
| Science | 194 | 56.0 | AA |
Scores de benchmarks (LLM Stats)
(LLM Stats (zeroeval))Agents
WideSearch
79.0%Aut.
DeepSearchQA
77.1%Aut.
BrowseCompOpenAI (2025)
74.9%Aut.
PaperBench
63.5%Aut.
Terminal-Bench 2.0Stanford × Laude Institute (2026)
50.8%Aut.
SWE-Bench ProPrinceton NLP (2024)
50.7%Aut.
CyberGym
41.3%Aut.
FrontierSWE
26.0%
Biology
GPQANYU + Cohere + Anthropic (2023)
87.6%Aut.
SciCode
48.7%Aut.
Code
SWE-Bench Verified
76.8%Aut.
SWE-bench Multilingual
73.0%Aut.
OJBench (C++)
57.4%Aut.
Economics
FinSearchComp T2&T3
67.8%Aut.
Finance
MMLU-Pro
87.1%Aut.
General
LiveCodeBench v6
85.0%Aut.
MMMU-Pro
78.5%Aut.
SimpleVQA
0.71 / 100Aut.
LiveBench
69.1%
LongBench v2
61.0%Aut.
Healthcare
VideoMMMU
86.6%Aut.
Image To Text
OCRBench
92.3%Aut.
Long Context
LongVideoBench
79.8%Aut.
LVBench
75.9%Aut.
AA-LCR
70.0%Aut.
Math
AIME 2025
96.1%Aut.
HMMT 2025
95.4%Aut.
MathVista-Mini
90.1%Aut.
MathVision
84.2%Aut.
IMO-AnswerBench
81.8%Aut.
Humanity's Last Exam
50.2%Aut.
Multimodal
InfoVQAtest
92.6%Aut.
OmniDocBench 1.5
88.8%Aut.
Video-MME
87.4%Aut.
MMVU
80.4%Aut.
CharXiv-R
77.5%Aut.
MotionBench
70.4%Aut.
WorldVQA
46.3%Aut.
ZEROBench
0.11 / 100Aut.
Reasoning
Seal-0
57.4%Aut.
Indices d'évaluation AA
(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
Scores par catégorie LLM Stats
(LLM Stats (zeroeval))Legal90
Language90
Finance90
Long Context80
Math80
Image To Text80
Frontend Development80
Video80
Multimodal70
Physics70
Reasoning70
Search70
Structured Output70
General70
Healthcare70
Biology70
Chemistry70
Vision70
Agents60
Code50
Tool Calling50
Safety40
Tarification
Prix d'entrée$0.6 / 1M tokens
Prix de sortie$3 / 1M tokens
Prix mixte (3:1)$1.2 / 1M tokens
Prix de lecture cache$0.095 / 1M tokens
Vitesse
Tokens/sec0.0
Délai du premier token0.00s
Temps de réponse0.00s
Classement des Prix par Fournisseur
Classement des Prix par Fournisseur
11 fournisseurs
Moins cher: NanoGPTPlus cher: Ofox
FournisseurEntréeSortie
1NanoGPTMoins cher
$0.3
$1.9
2TensorX
$0.5
$2.8
3OpenRouter
$0.57
$2.85
4ZenMux
$0.58
$3.02
5KimiPRINCIPAL
$0.6
$3
6Jiekou.AI
$0.6
$3
7NovitaAI
$0.6
$3
8Kilo Gateway
$0.6
$3
9Vercel AI Gateway
$0.6
$3
10HPC-AI
$0.6
$3
11Ofox
$0.6
$3
Comparer les prix entre différents fournisseurs API pour ce modèle.