Expired60% confidenceBenchmarkExact time
GPT-5.6 Sol leads in performance on the Browse Comp and Agent's Last Exam evaluations.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
7/12/2026
First Seen
Valid until: 10/10/2026(expired)
Sources
ChatGPT Work Officially Launches: How GPT-5.6 Is Reshaping the Way You Work
bilibiliGoldenSpiderAI7/9/2026
Related Claims
UnverifiedWhen 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 research80% similarUnverifiedUnder the weighted index, GPT-5.6 Sol achieved the highest taste score by a significant margin, and this was a blind test result.78% similarVerifiedGPT-5.6 Sol achieves state of the art on the coding benchmark Terminal Bench.77% similarUnverifiedGPT-5.6 achieves state-of-the-art results on Terminal Bench, BrowseComp, and Agent's Last Exam, and on the DeepSuite evaluation delivers better performance at less than half the cost of competing products76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/490918API
curl https://kongchang.com/api/v1/knowledge/claims/490918MCP
get_claim(id=490918)