Claude Sonnet 4.6 vs GPT-OSS 120B
Side-by-side benchmark comparison across coding, math, reasoning, speed, and pricing.
Claude Sonnet 4.6 by Anthropic wins on 7 of 12 benchmarks against GPT-OSS 120B by OpenAI, which leads on 5. This head-to-head comparison covers coding, math, reasoning, speed, and pricing metrics from our benchmark data.
Category-by-Category Breakdown
General Intelligence: In general intelligence, Claude Sonnet 4.6 scores 30.5 on AA Intelligence Index compared to GPT-OSS 120B's 12.3.
Coding: In coding, Claude Sonnet 4.6 scores 63 on AA Coding Index compared to GPT-OSS 120B's 30.4, while Claude Sonnet 4.6 scores 1274 on Design Arena ELO compared to GPT-OSS 120B's 974, while Claude Sonnet 4.6 scores 1297 on Website Arena ELO compared to GPT-OSS 120B's 980.
Reasoning: In reasoning, GPT-OSS 120B scores 74.9% on GPQA Diamond compared to Claude Sonnet 4.6's 54.3%, while Claude Sonnet 4.6 scores 33.1 on AA Agentic Index compared to GPT-OSS 120B's 6.2, while Claude Sonnet 4.6 scores 75.3% on τ²-Bench Airline compared to GPT-OSS 120B's 64.1%.
Context: In context, Claude Sonnet 4.6 scores 1.0M on Context Length compared to GPT-OSS 120B's 131K.
Pricing Comparison
Claude Sonnet 4.6 costs $3.0/1M input tokens and $15.0/1M output tokens, while GPT-OSS 120B costs $0.04/1M input and $0.17/1M output. GPT-OSS 120B is the more affordable option for API usage.
Speed Comparison
Claude Sonnet 4.6 generates output at 57 tok/s compared to GPT-OSS 120B's 339 tok/s, and the time to first token is 790 ms for Claude Sonnet 4.6 versus 440 ms for GPT-OSS 120B. GPT-OSS 120B delivers faster throughput.
Verdict
GPT-OSS 120B leads across the board in affordability, speed, making it the stronger overall choice in this comparison.
View Individual Model Pages
Claude Sonnet 4.6 vs GPT-OSS 120B — FAQ
Which is better, Claude Sonnet 4.6 or GPT-OSS 120B?
Claude Sonnet 4.6 wins on more benchmarks overall (7 vs 5). However, the best choice depends on your specific needs — each model excels in different areas.
How does Claude Sonnet 4.6 compare to GPT-OSS 120B for coding?
SWE-bench Verified data is not available for both models. Check the detailed comparison charts above for other coding-related metrics.
Is Claude Sonnet 4.6 cheaper than GPT-OSS 120B?
Yes, GPT-OSS 120B is cheaper. Claude Sonnet 4.6 costs $3.0/1M input and $15.0/1M output tokens. GPT-OSS 120B costs $0.04/1M input and $0.17/1M output tokens.
Which is faster, Claude Sonnet 4.6 or GPT-OSS 120B?
GPT-OSS 120B is faster, generating output at 339 tok/s compared to 57 tok/s. Faster output speed means shorter wait times for API responses.
What benchmarks does the Claude Sonnet 4.6 vs GPT-OSS 120B comparison cover?
This comparison covers 12 benchmarks including GPQA Diamond, Output Speed, Time to First Token, Input Cost, Output Cost, Context Length, AA Intelligence Index, AA Coding Index, and more. Metrics span general intelligence, coding, math, reasoning, speed, and cost categories.