Unverified50% confidenceBenchmarkExact time
In CAD World's 200-task evaluation, the best-performing GPT-5.4 achieved a success rate of only 17.5%.
1
Sources
50%
Confidence
Long-term
Relevance
9/26/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn EvoArena testing, GPT-5.5, which achieved the highest Step Level score, had an accuracy of just over 50%, while Gemini-3.1 Pro and GLM-5.1, which performed best at the Chain Level, reached only approximately 28%–29%.78% similarUnverifiedIn the Automation Bench test, GPT-6 Sol's extra high tier achieved first place 33% of the time, while 5.6's max effort scored 28.8.74% similarUnverifiedOn the HLE benchmark, COMED improved GPT-5.5's performance from 23.1% to 28.1%.73% similarUnverified在长周期智能体工作流测试（Engines Last Exam）中，GPT-5.6 Sol 得分 53.6，比 Faber-5 高出 13.1 分73% similarUnverifiedIn the Agents' Last Exam benchmark, GPT-5.6 Sol achieved a score of 53.6, which is 13.1 points higher than Claude Fable 5 using adaptive reasoning.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/951467API
curl https://kongchang.com/api/v1/knowledge/claims/951467MCP
get_claim(id=951467)