Expired80% confidenceFactTime unknown
According to Anthropic's official data, Haiku 4.5 outperformed Sonnet 4 on SWE-bench and even surpassed GPT-5
1
Sources
80%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedAnthropic claims that Sonnet 4.5 outperforms GPT-5 on coding tasks.73% similarUnverifiedGLM-4.7 surpasses DeepSeek V3.2 and GPT-5.1 in browser capability tests, clearly leading Claude Sonnet 4.5.71% similarUnverifiedThe article claims that Claude Haiku 4.5 outperformed GPT-5 and Gemini 2.5 Pro on several core benchmarks.70% similarUnverifiedIn a SaaS landing page generation test, all four models (Claude Haiku 4.5, Claude Sonnet 4.0, Gemini 2.5 Pro, and GPT-5) successfully completed the task, but Haiku 4.5 generated results the fastest.70% similarUnverifiedThe three-tier model lineup of GPT-5.6 is positioned against Anthropic's flagship Opus, mid-range Sonnet, and efficient Haiku.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/24313API
curl https://kongchang.com/api/v1/knowledge/claims/24313MCP
get_claim(id=24313)