Unverified50% confidenceBenchmarkExact time
In automated business process testing, GPT-6 Sol outperformed Claude Opus 5, with a per-task cost of approximately 9% of the latter.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/29/2026
First Seen
Valid until: 12/28/2026
Sources
Related Entities
Related Claims
UnverifiedThe per-task cost of GPT-6 Sol High on Automation Bench is only one-tenth that of Opus 5.79% similarPartially VerifiedAll three GPT-5.6 models achieved a perfect score of 10 on the long-horizon agent fine-tuning task, while GPT-5.5 and Opus 4.7 could only score two or three points on that task.76% similarUnverifiedOn difficult math problems, both SOL and TERRA achieved perfect scores of 10, and on the adaptive fine-tuning task all three GPT-5.6 models achieved perfect scores, whereas the previous GPT-5.5 and Opus 4.7 could only score two to three points on the same task.75% similarUnverifiedGPT-6 Sol and GPT-6 Luna deliver strong performance at lower cost and have pushed the Pareto frontier on the OfficeQA Pro benchmark75% similarUnverifiedThe full TwinCheck strategy improved the task success rate of the GPT-5.6 Sol model from 45.3% to 58.5%, with a 95% task bootstrap confidence interval of [8.2, 18.8].74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/958996API
curl https://kongchang.com/api/v1/knowledge/claims/958996MCP
get_claim(id=958996)