+
+
+
+
+
+
+
+
VS
VS
VS
VS
VS
VS
Llama 3.2 90B Instruct vs Llama 3.3 70B Instruct
Comprehensive side-by-side LLM comparison
Llama 3.3 70B Instruct leads with 4.3% higher average benchmark score. Both models have similar pricing. Llama 3.2 90B Instruct supports multimodal inputs. Llama 3.3 70B Instruct is available on 9 providers. 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 3.3 70B was introduced with refinements to the Llama 3 architecture, designed to incorporate improvements in instruction-following and task performance. Built to continue the evolution of Meta's 70B tier, it provides enhanced quality while maintaining the deployment characteristics valued by the open-source community.
2 months newer
Llama 3.2 90B Instruct
Meta
2024-09-25
Llama 3.3 70B Instruct
Meta
2024-12-06
+
+
+
+
+
+
+
+
+
+
+
+
Pricing Comparison
Cost per million tokens (USD)
+
+
+
+
Llama 3.2 90B Instruct
Input:$0.35
Output:$0.40
+
+
+
+
Llama 3.3 70B Instruct
Input:$0.20
Output:$0.20($0.35 cheaper)
Performance Metrics
Context window and performance specifications
Average performance across 4 common benchmarks
+
+
+
+
Llama 3.2 90B Instruct
Average Score:71.9%
+
+
+
+
Llama 3.3 70B Instruct
Average Score:76.1%(+4.3%)
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:71.9%
Providers:5
+
+
+
+
Llama 3.3 70B Instruct
Avg Score:76.1%(+4.3%)
Providers:9