Comprehensive side-by-side LLM comparison
Llama 3.2 90B Instruct leads with 26.4% higher average benchmark score. Kimi K2 0905 offers 268.3K more tokens in context window than Llama 3.2 90B Instruct. Llama 3.2 90B Instruct is $2.35 cheaper per million tokens. Llama 3.2 90B Instruct supports multimodal inputs. Llama 3.2 90B Instruct is available on 5 providers. Overall, Llama 3.2 90B Instruct is the stronger choice for coding tasks.
Moonshot AI
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.
Meta
Llama 3.2 90B Instruct is a multimodal language model developed by Meta. It achieves strong performance with an average score of 71.3% across 13 benchmarks. It excels particularly in AI2D (92.3%), DocVQA (90.1%), MGSM (86.9%). It supports a 256K token context window for handling large documents. The model is available through 5 API providers. As a multimodal model, it can process and understand text, images, and other input formats seamlessly. It's licensed for commercial use, making it suitable for enterprise applications. Released in 2024, it represents Meta's latest advancement in AI technology.
11 months newer
Llama 3.2 90B Instruct
Meta
2024-09-25
Kimi K2 0905
Moonshot AI
2025-09-05
Cost per million tokens (USD)
Kimi K2 0905
Llama 3.2 90B Instruct
Context window and performance specifications
Average performance across 16 common benchmarks
Kimi K2 0905
Llama 3.2 90B Instruct
Available providers and their performance metrics
Kimi K2 0905
Novita
ZeroEval
Llama 3.2 90B Instruct
Kimi K2 0905
Llama 3.2 90B Instruct
Kimi K2 0905
Llama 3.2 90B Instruct
Bedrock
DeepInfra
Fireworks
Hyperbolic
Together