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 scored 69.2% on the SWE-bench benchmark, compared to 58.6% for GPT 5.5 and 54.2% for Google Gemini.76% similarUnverifiedThe median output token count per problem-solving attempt for Opus 4.7 is 60,000, while GPT 5.5 requires only 16,000.75% 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% similarUnverifiedOn the virology multiple-choice benchmark, Mythos 5 scores 56% and GPT-5.6 Sol scores 55.5%, nearly tied and both far exceeding the expert baseline.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)