Unverified50% confidenceBenchmarkExact time
据非官方爆料，Terminal Bench 3.0基准测试中Claude Opus 5 Max以43.5%的得分超越GPT-5.6-Sol的34.6%重登榜首
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
8/23/2026
First Seen
Valid until: 9/6/2026
Sources
Related Entities
Related Claims
UnverifiedGPT-5.6在Agent's Last Exam测试中以53.6分创下历史新高，领先Claude Opus 4.5达13.1分80% similarUnverifiedClaude Opus 4.6在SWE-Bench Pro测试中得分为53.4%77% similarPartially 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% similarUnverified在Diamond子集中，Claude 3.0 Opus得分5.2%，Gemini 1.5 Pro得分4.7%，GPT-4o Mini得分4.6%，Kimi K2.6得分3.8%74% similarUnverifiedClaude Opus 4.7在SWE Bench Pro上得分从53.4%提升至54.3%74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/789694API
curl https://kongchang.com/api/v1/knowledge/claims/789694MCP
get_claim(id=789694)