Moonshot AI

Kimi-k1.5

Multimodal
Zero-eval
#1CLUEWSC
#1LiveCodeBench v5 24.12-25.2
#2C-Eval
+1 more

by Moonshot AI

+
+
+
+
About

Kimi K1.5 was developed by Moonshot AI as an advanced language model with extended context capabilities, designed to handle long documents and conversations. Built to excel at tasks requiring comprehension of extensive information, it represents Moonshot's approach to long-context language understanding.

+
+
+
+
Timeline
AnnouncedJan 20, 2025
ReleasedJan 20, 2025
+
+
+
+
Specifications
Capabilities
Multimodal
+
+
+
+
License & Family
License
Proprietary
Performance Overview
Performance metrics and category breakdown

Overall Performance

9 benchmarks
Average Score
81.7%
Best Score
96.2%
High Performers (80%+)
5
+
+
+
+
All Benchmark Results for Kimi-k1.5
Complete list of benchmark scores with detailed information
MATH-500
text
0.96
96.2%
Self-reported
CLUEWSC
text
0.91
91.4%
Self-reported
C-Eval
text
0.88
88.3%
Self-reported
MMLU
text
0.87
87.4%
Self-reported
IFEval
text
0.87
87.2%
Self-reported
AIME 2024
text
0.78
77.5%
Self-reported
MathVista
multimodal
0.75
74.9%
Self-reported
MMMU
multimodal
0.70
70.0%
Self-reported
LiveCodeBench v5 24.12-25.2
text
0.63
62.5%
Self-reported
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+