Unverified50% confidenceReleaseExact time
The default speed of GPT-6 Astra and GPT-6.1 Sol has increased by approximately 50%, with the target rising from 30 tokens per second to approximately 50 tokens per second.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/6/2026
First Seen
Valid until: 1/4/2027
Sources
Related Entities
Related Claims
VerifiedGPT-5.6 Sol will be available on the Cerebras platform, achieving an inference speed of 750 tokens per second.78% similarUnverifiedWhen processing a tax workbook containing 50 tabs, GPT-6 Astra completed the task at twice the speed of the previous generation GPT-5.6 Sol.77% similarUnverifiedGPT-6 (Astral) achieved an accuracy rate of 72.6% on the OS World 2.0 benchmark, with an average of approximately 40 minutes per task.72% similarUnverifiedOn performance model code construction tasks, GPT-5.6 Sol achieved a pass rate exceeding 80%.72% similarPartially VerifiedGPT-5.6 has improved the prompt caching mechanism by adding explicit cache breakpoints, with a minimum cache retention of 30 minutes and output speeds of up to hundreds of tokens per second.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/980091API
curl https://kongchang.com/api/v1/knowledge/claims/980091MCP
get_claim(id=980091)