Comprehensive side-by-side LLM comparison
Gemini 2.5 Pro Preview 06-05 leads with 30.7% higher average benchmark score. Gemini 2.5 Pro Preview 06-05 offers 858.1K more tokens in context window than Llama 3.2 90B Instruct. Llama 3.2 90B Instruct is $10.50 cheaper per million tokens. Llama 3.2 90B Instruct is available on 5 providers. Overall, Gemini 2.5 Pro Preview 06-05 is the stronger choice for coding tasks.
Gemini 2.5 Pro Preview was released as an early access version of Gemini 2.5 Pro, designed to allow developers and enterprises to experiment with next-generation capabilities before general availability. Built to gather feedback and demonstrate upcoming features, it provided a window into the evolution of Google's flagship model.
Meta
Llama 3.2 90B was developed as a flagship-tier open-source model, designed to provide advanced capabilities with 90 billion parameters. Built to serve applications requiring high-quality reasoning and generation, it represents a powerful option within the Llama 3.2 series for demanding tasks.
8 months newer

Llama 3.2 90B Instruct
Meta
2024-09-25

Gemini 2.5 Pro Preview 06-05
2025-06-05
Cost per million tokens (USD)

Gemini 2.5 Pro Preview 06-05

Llama 3.2 90B Instruct
Context window and performance specifications
Average performance across 2 common benchmarks

Gemini 2.5 Pro Preview 06-05

Llama 3.2 90B Instruct
Gemini 2.5 Pro Preview 06-05
2025-01-31
Available providers and their performance metrics

Gemini 2.5 Pro Preview 06-05

Llama 3.2 90B Instruct

Gemini 2.5 Pro Preview 06-05

Llama 3.2 90B Instruct

Gemini 2.5 Pro Preview 06-05

Llama 3.2 90B Instruct
Bedrock
DeepInfra
Fireworks
Hyperbolic
Together