Expired50% confidenceBenchmarkExact time
On Terminal Bench 2.1, Sol in Ultra mode approached 92%, surpassing Mythos 5's 88%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/8/2026
First Seen
Valid until: 10/6/2026(expired)
Sources
GPT-5.6 Sol对决Fable 5：半价能否媲美旗舰？
bilibiliYoutube力工7/6/2026
Related Claims
UnverifiedOn the Terminal Bench 2.1 benchmark, GPT-5.6 Sol's Ultra mode approaches 92%, surpassing the competing product's performance of 88%.73% similarUnverifiedOn the Exploit Bench cybersecurity benchmark, Sol scores approximately 76% and Mythos 5 approximately 78%.73% similarUnverifiedThe standard version of Sol scored 88.8% on the Terminal Bench 2.1 benchmark, which improved to 91.9% with Ultra mode enabled.68% similarUnverifiedOn Artificial Analysis's Omniscience hallucination metric, GPT-5.6 Sol Max reached 89%, higher than Claude Fable's 55% and GLM 5.2's 28%.67% similarUnverifiedOn the SWE-Bench Pro programming benchmark, Claude Fable 5 leads with a score of 80%, ahead of GPT-5.6 Sol's 64.6%.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/249746API
curl https://kongchang.com/api/v1/knowledge/claims/249746MCP
get_claim(id=249746)