Comprehensive side-by-side LLM comparison
Kimi K2 0905 leads with 34.8% higher average benchmark score. Kimi K2 0905 offers 268.3K more tokens in context window than Phi-3.5-mini-instruct. Phi-3.5-mini-instruct is $2.90 cheaper per million tokens. Overall, Kimi K2 0905 is the stronger choice for coding tasks.
Moonshot AI
Kimi K2 was introduced as the second generation of Moonshot's language model family, designed to provide enhanced capabilities across language understanding and generation. Built with architectural improvements and expanded training, it represents a significant advancement in Moonshot's model offerings.
Microsoft
Phi-3.5 Mini was developed by Microsoft as a small language model designed to deliver impressive performance despite its compact size. Built with efficiency in mind, it demonstrates that capable language understanding and generation can be achieved with fewer parameters, making AI more accessible for edge and resource-constrained deployments.
1 year newer

Phi-3.5-mini-instruct
Microsoft
2024-08-23

Kimi K2 0905
Moonshot AI
2025-09-05
Cost per million tokens (USD)

Kimi K2 0905

Phi-3.5-mini-instruct
Context window and performance specifications
Average performance across 5 common benchmarks

Kimi K2 0905

Phi-3.5-mini-instruct
Available providers and their performance metrics

Kimi K2 0905
Novita
ZeroEval

Phi-3.5-mini-instruct

Kimi K2 0905

Phi-3.5-mini-instruct

Kimi K2 0905

Phi-3.5-mini-instruct
Azure