Kimi-k1.5

Unknown Developer

Kimi 1.5, created by Moonshot AI, represents a significant advancement in multimodal large language models. By utilizing sophisticated reinforcement learning techniques and scalable multimodal reasoning, Kimi 1.5 achieves cutting-edge results in areas such as mathematics, coding, image analysis, and complex, long-context problem-solving.

Model Specifications

Technical details and capabilities of Kimi-k1.5

Core Specifications

128.0K / 128.0K

Input / Output tokens

January 19, 2025

Release date

Capabilities & License

Multimodal Support
Supported
Web Hydrated
Yes
License
Proprietary

Resources

Research Paper
https://arxiv.org/abs/2501.12599
API Reference
https://platform.moonshot.cn/docs/api-reference
Playground
https://kimi.ai/
Code Repository
https://github.com/MoonshotAI/Kimi-k1.5

Performance Insights

Check out how Kimi-k1.5 handles various AI tasks through comprehensive benchmark results.

100
75
50
25
0
96.2
MATH-500
96.2
(96%)
94
Codeforces
94
(94%)
91.4
CLUEWSC
91.4
(91%)
88.3
C-EVAL
88.3
(88%)
87.4
MMLU
87.4
(87%)
87.2
IF-Eval
87.2
(87%)
77.5
AIME 2024
77.5
(78%)
74.9
MathVista
74.9
(75%)
70
MMMU
70
(70%)
62.5
LiveCodeBench
62.5
(63%)
MATH-500
Codeforces
CLUEWSC
C-EVAL
MMLU
IF-Eval
AIME 2024
MathVista
MMMU
LiveCodeBench

Model Comparison

See how Kimi-k1.5 stacks up against other leading models across key performance metrics.

100
80
60
40
20
0
87.4
MMLU - Kimi-k1.5
87.4
(87%)
87.5
MMLU - Grok-2
87.5
(88%)
90.4
MMLU - Claude 3.5 Sonnet
90.4
(90%)
85.9
MMLU - Gemini 1.5 Pro
85.9
(86%)
91.8
MMLU - o1
91.8
(92%)
86.2
MMLU - Grok-2 mini
86.2
(86%)
74.9
MathVista - Kimi-k1.5
74.9
(75%)
69
MathVista - Grok-2
69
(69%)
67.7
MathVista - Claude 3.5 Sonnet
67.7
(68%)
68.1
MathVista - Gemini 1.5 Pro
68.1
(68%)
71
MathVista - o1
71
(71%)
68.1
MathVista - Grok-2 mini
68.1
(68%)
70
MMMU - Kimi-k1.5
70
(70%)
66.1
MMMU - Grok-2
66.1
(66%)
68.3
MMMU - Claude 3.5 Sonnet
68.3
(68%)
65.9
MMMU - Gemini 1.5 Pro
65.9
(66%)
77.3
MMMU - o1
77.3
(77%)
63.2
MMMU - Grok-2 mini
63.2
(63%)
MMLU
MathVista
MMMU
Kimi-k1.5
Grok-2
Claude 3.5 Sonnet
Gemini 1.5 Pro
o1
Grok-2 mini

Detailed Benchmarks

Dive deeper into Kimi-k1.5's performance across specific task categories. Expand each section to see detailed metrics and comparisons.

Math

AIME 2024

Current model
Other models
Avg (66.2%)

MATH-500

Current model
Other models
Avg (93.4%)

Coding

Codeforces

90.0%
79.0%
68.0%
47.0%
41.3%
Current model
Other models
Avg (62.8%)

LiveCodeBench

Current model
Other models
Avg (58.2%)

Knowledge

MMLU

Current model
Other models
Avg (85.6%)

Non categorized

MathVista

Current model
Other models
Avg (70.1%)

MMMU

Current model
Other models
Avg (64.6%)

CLUEWSC

Current model
Other models
Avg (91.7%)

Providers Pricing Coming Soon

We're working on gathering comprehensive pricing data from all major providers for Kimi-k1.5. Compare costs across platforms to find the best pricing for your use case.

OpenAI
Anthropic
Google
Mistral AI
Cohere

Share your feedback

Hi, I'm Charlie Palars, the founder of Deepranking.ai. I'm always looking for ways to improve the site and make it more useful for you. You can write me through this form or directly through X at @palarsio.

Your feedback helps us improve our service

Stay Ahead with AI Updates

Get insights on Gemini Pro 2.5, Sonnet 3.7 and more top AI models