Unverified50% confidenceBenchmarkExact time
Claude Opus 5在智能体搜索BrowseComp上得分30.8%，与GPT系列基本持平；工具增强多学科推理64.7%；生物学人类可解问题上高达90.1%
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/23/2026
First Seen
Valid until: 11/21/2026
Sources
Related Entities
Related Claims
Partially VerifiedClaude Opus 4.8在SWE-bench基准测试中得分69.2%，GPT 5.5为58.6%，Google Gemini为54.2%76% similarUnverifiedOpus 4.7每次解题的中位输出token数为60,000，而GPT 5.5仅需16,00075% similarUnverifiedClaude Opus 4.8在AI Coding基准测试中表现超越GPT-5.573% similarUnverified在GPT-4发布初期，主流模型在GPQA上的准确率约为35-40%，人类领域专家基准线约为65%，随机猜测为25%72% similarUnverified在病毒学多选基准上，Mythos 5得分56%，GPT-5.6 Sol得分55.5%，几乎持平且均远超专家基线71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/789652API
curl https://kongchang.com/api/v1/knowledge/claims/789652MCP
get_claim(id=789652)