+
+
+
+
+
+
+
+
VS
VS
VS
VS
VS
VS
Llama 3.2 90B Instruct vs Llama 4 Scout
Comprehensive side-by-side LLM comparison
Llama 4 Scout leads with 2.5% higher average benchmark score. Llama 4 Scout offers 19.7M more tokens in context window than Llama 3.2 90B Instruct. Both models have similar pricing. Both models have their strengths depending on your specific coding needs.
+
+
+
+
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.
+
+
+
+
Meta
Llama 4 Scout was created as an exploratory variant in the Llama 4 family, designed to investigate new architectures and optimization strategies. Built as part of Meta's commitment to advancing open-source AI, it serves as a testbed for innovations that may inform future model releases.
6 months newer
Llama 3.2 90B Instruct
Meta
2024-09-25
Llama 4 Scout
Meta
2025-04-05
+
+
+
+
+
+
+
+
+
+
+
+
Pricing Comparison
Cost per million tokens (USD)
+
+
+
+
Llama 3.2 90B Instruct
Input:$0.35
Output:$0.40
+
+
+
+
Llama 4 Scout
Input:$0.08
Output:$0.30($0.37 cheaper)
Performance Metrics
Context window and performance specifications
Average performance across 8 common benchmarks
+
+
+
+
Llama 3.2 90B Instruct
Average Score:72.6%
+
+
+
+
Llama 4 Scout
Average Score:75.1%(+2.5%)
Provider Availability & Performance
Available providers and their performance metrics
+
+
+
+
Llama 3.2 90B Instruct
5 providers
Bedrock
Throughput: 100 tok/s
Latency: 0.5ms
DeepInfra
Throughput: 24 tok/s
Latency: 0.5ms
Fireworks
Throughput: 50 tok/s
Latency: 0.5ms
Hyperbolic
Throughput: 42 tok/s
Latency: 0.5ms
Together
+
+
+
+
Llama 3.2 90B Instruct
Avg Score:72.6%
Providers:5
+
+
+
+
Llama 4 Scout
Avg Score:75.1%(+2.5%)
Providers:6