Kimi K2 0905
Zero-eval
#1HumanEval
by Moonshot AI
+
+
+
+
About
Kimi K2 0905 is a language model developed by Moonshot AI. This model demonstrates exceptional performance with an average score of 84.0% across 6 benchmarks. It excels particularly in HumanEval (94.5%), MMLU (90.2%), MATH (89.1%). It supports a 524K token context window for handling large documents. The model is available through 2 API providers. Released in 2025, it represents Moonshot AI's latest advancement in AI technology.
+
+
+
+
Pricing Range
Input (per 1M)$0.60 -$0.60
Output (per 1M)$2.50 -$2.50
Providers2
+
+
+
+
Timeline
AnnouncedSep 5, 2025
ReleasedSep 5, 2025
+
+
+
+
License & Family
License
Proprietary
Base ModelKimi K2 Instruct
Performance Overview
Performance metrics and category breakdown
Overall Performance
6 benchmarks
Average Score
84.0%
Best Score
94.5%
High Performers (80%+)
4Performance Metrics
Max Context Window
524.3K+
+
+
+
All Benchmark Results for Kimi K2 0905
Complete list of benchmark scores with detailed information
| HumanEval | text | 0.94 | 94.5% | Self-reported | |
| MMLU | text | 0.90 | 90.2% | Self-reported | |
| MATH | text | 0.89 | 89.1% | Self-reported | |
| MMLU-Pro | text | 0.82 | 82.5% | Self-reported | |
| GPQA | text | 0.76 | 75.8% | Self-reported | |
| AIME 2024 | text | 0.72 | 72.0% | Self-reported |