Unverified50% confidenceBenchmarkExact time
In OpenAI's LiveWork test, GPT-6.2 Sol outperformed the older GPT-6 Astra, at a task cost of about one-seventh of the latter's.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
11/18/2026
First Seen
Valid until: 12/2/2026
Sources
Related Entities
Related Claims
UnverifiedIn automated business process testing, GPT-6 Sol outperformed Claude Opus 5, with a per-task cost of approximately 9% of the latter.80% similarUnverifiedIn the T3 code improvement task, GPT-6.1 Sol scored 87.4, beating Astra (83.8) and Grok 4.7 (80.7), at a cost of only $2.15.77% similarUnverifiedAccording to the YouTube channel World of AI, OpenAI's next-generation internal model GPT-6.2 Astra scores 0.875 on BenchCAD 2.0, while the current GPT-6 Astra scores 0.594.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1185135API
curl https://kongchang.com/api/v1/knowledge/claims/1185135MCP
get_claim(id=1185135)