Expired60% confidenceOpinionTime unknown
In a Snake game code generation test, the code generation quality of GPT-OSS 120B was essentially on par with O4 Mini, performing better in certain details.
1
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedThe GPT-OSS 120B version activates only 5.1B parameters during inference and achieves performance close to O4-mini.74% similarUnverifiedGPT-OSS 20B is capable of successfully generating runnable game program code.71% similarUnverifiedThe GPT-OSS 20B version activates only 3.6B parameters during inference and achieves performance close to O3-mini.71% similarUnverifiedGPT-4o-mini has fast inference speed and low cost, making it suitable for everyday lightweight coding and code completion.71% similarUnverifiedThe performance of GPT-OSS 120B is comparable to OpenAI O4 Mini.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/23254API
curl https://kongchang.com/api/v1/knowledge/claims/23254MCP
get_claim(id=23254)