Comprehensive side-by-side LLM comparison
Gemini 2.0 Flash Thinking leads with 21.3% higher average benchmark score. Llama 3.2 90B Instruct is available on 5 providers. Overall, Gemini 2.0 Flash Thinking is the stronger choice for coding tasks.
Gemini 2.0 Flash Thinking was developed to incorporate extended reasoning capabilities into the Flash family, designed to combine quick response times with deeper analytical processing. Built to handle tasks requiring both speed and thoughtful problem-solving, it bridges the gap between fast inference and reasoning-enhanced models.
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.
3 months newer

Llama 3.2 90B Instruct
Meta
2024-09-25

Gemini 2.0 Flash Thinking
2025-01-21
Context window and performance specifications
Average performance across 2 common benchmarks

Gemini 2.0 Flash Thinking

Llama 3.2 90B Instruct
Gemini 2.0 Flash Thinking
2024-08-01
Available providers and their performance metrics

Gemini 2.0 Flash Thinking

Llama 3.2 90B Instruct
Bedrock

Gemini 2.0 Flash Thinking

Llama 3.2 90B Instruct

Gemini 2.0 Flash Thinking

Llama 3.2 90B Instruct
DeepInfra
Fireworks
Hyperbolic
Together