+
+
+
+
+
+
+
+
VS
VS
VS
VS
VS
VS
Llama 3.2 90B Instruct vs Llama 4 Maverick
Comprehensive side-by-side LLM comparison
Llama 4 Maverick leads with 8.2% higher average benchmark score. Llama 4 Maverick offers 1.7M more tokens in context window than Llama 3.2 90B Instruct. Both models have similar pricing. Llama 4 Maverick is available on 7 providers. Overall, Llama 4 Maverick is the stronger choice for coding tasks.
+
+
+
+
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 Maverick was developed as a variant in Meta's fourth-generation language model family, designed to explore specialized capabilities and training approaches. Built to push the boundaries of open-source model development, it represents experimentation with advanced techniques in the Llama lineage.
6 months newer
Llama 3.2 90B Instruct
Meta
2024-09-25
Llama 4 Maverick
Meta
2025-04-05
+
+
+
+
+
+
+
+
+
+
+
+
Pricing Comparison
Cost per million tokens (USD)
+
+
+
+
Llama 3.2 90B Instruct
Input:$0.35
Output:$0.40($0.02 cheaper)
+
+
+
+
Llama 4 Maverick
Input:$0.17
Output:$0.60
Performance Metrics
Context window and performance specifications
Average performance across 9 common benchmarks
+
+
+
+
Llama 3.2 90B Instruct
Average Score:69.6%
+
+
+
+
Llama 4 Maverick
Average Score:77.8%(+8.2%)
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:69.6%
Providers:5
+
+
+
+
Llama 4 Maverick
Avg Score:77.8%(+8.2%)
Providers:7