Verified70% confidenceBenchmarkExact time
GPT-6.1 Sol performs best on the DeepSWE benchmark at the high reasoning effort level
4
Sources
70%
Confidence
Medium-term (~90 days)
Relevance
9/30/2026
First Seen
Valid until: 12/29/2026
Sources
Related Entities
Related Claims
UnverifiedGPT-5.6 Sol introduces two new reasoning levels, Max and Ultra.80% similarUnverifiedWhen reasoning is set to High, GPT-6.1 Sol scores highest in professional work and scientific research scenarios, far surpassing Opus 5.5 in scientific research79% similarUnverifiedGPT-5.6 flagship version Sol achieves significant capability improvements in three professional domains—coding, biology, and cybersecurity—and introduces the Max reasoning compute option and Ultra mode.79% similarUnverifiedSol 是三款模型中能力最强的，价格与 GPT-5.5 持平，适合复杂 coding 与长任务场景78% similarVerifiedGPT-5.6 Sol is an all-new flagship model focused on complex reasoning and agentic programming.78% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/961562API
curl https://kongchang.com/api/v1/knowledge/claims/961562MCP
get_claim(id=961562)