+
+
+
+
+
+
+
+
VS
VS
VS
VS
VS
VS
Command R+ vs GPT OSS 120B
Comprehensive side-by-side LLM comparison
GPT OSS 120B leads with 14.3% higher average benchmark score. GPT OSS 120B offers 6.1K more tokens in context window than Command R+. GPT OSS 120B is $0.71 cheaper per million tokens. GPT OSS 120B is available on 5 providers. Overall, GPT OSS 120B is the stronger choice for coding tasks.
+
+
+
+
Cohere
Command R+ was developed by Cohere as an advanced language model designed for enterprise applications requiring retrieval-augmented generation. Built to excel at combining external knowledge with language understanding, it serves businesses needing reliable, factually-grounded AI assistance with strong reasoning and multilingual capabilities.
+
+
+
+
OpenAI
GPT-OSS 120B was developed as an open-source model release from OpenAI, designed to provide the research and developer community with access to a capable language model. Built with 120 billion parameters, it enables experimentation, fine-tuning, and deployment in contexts where open-source licensing and transparency are valued.
11 months newer
Command R+
Cohere
2024-08-30
GPT OSS 120B
OpenAI
2025-08-05
+
+
+
+
+
+
+
+
+
+
+
+
Pricing Comparison
Cost per million tokens (USD)
+
+
+
+
Command R+
Input:$0.25
Output:$1.00
+
+
+
+
GPT OSS 120B
Input:$0.09
Output:$0.45($0.71 cheaper)
Performance Metrics
Context window and performance specifications
Average performance across 1 common benchmarks
+
+
+
+
Command R+
Average Score:75.7%
+
+
+
+
GPT OSS 120B
Average Score:90.0%(+14.3%)
Provider Availability & Performance
Available providers and their performance metrics
+
+
+
+
Command R+
2 providers
Bedrock
Throughput: 100 tok/s
Latency: 0.5ms
Cohere
Throughput: 59 tok/s
Latency: 0.65ms
+
+
+
+
+
+
+
+
Command R+
Avg Score:75.7%
Providers:2
+
+
+
+
GPT OSS 120B
Avg Score:90.0%(+14.3%)
Providers:5