Expired80% confidenceFactTime unknown
Haiku 4.5's agentic tool use score reached 83%, while Claude 4 scored only 9.6%
1
Sources
80%
Confidence
Medium-term (~90 days)
Relevance
6/3/2026
First Seen
Valid until: 9/1/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedHaiku 4.5's Agent tool use score is 83%, far exceeding Claude 4's 9.6%.85% similarPartially VerifiedClaude Haiku 4.5 achieved a score of 73.3% on the SWE-bench benchmark.78% similarUnverifiedHaiku 4.5's Agent Coding score is approximately 5 percentage points higher than Claude 4.78% similarUnverifiedClaude Haiku 4.5 scored 83.2% on the retail benchmark for agentic tool use, 63.6% on airline tasks, and 83% on telecom tasks.74% similarUnverifiedClaude Haiku 4.5 scored 96.3% on high school math competition tasks with tool assistance and 80.7% without tools.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/40312API
curl https://kongchang.com/api/v1/knowledge/claims/40312MCP
get_claim(id=40312)