Expired65% confidenceFactTime unknown
In an independent tester's overall rankings, Claude 4.5 Haiku placed 34th and 37th respectively, making it the lowest-scoring next-generation model among mainstream AI labs.
1
Sources
65%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedClaude Haiku 4.5 scored 83.2% on the retail benchmark for agentic tool use, 63.6% on airline tasks, and 83% on telecom tasks.73% similarUnverifiedClaude Haiku 4.5 achieved the fastest generation speed and lowest cost across the three front-end test scenarios.73% similarUnverifiedThe independent tester ran tests on Claude 4.5 Haiku more than five times repeatedly, and the results consistently showed poor performance.71% similarUnverifiedClaude Haiku 4.5 has a lower false refusal rate than Sonnet 4.5 and Opus 4.1, making it one of the safest models Anthropic has released to date.69% similarUnverifiedHaiku 4.5's agentic tool use score reached 83%, while Claude 4 scored only 9.6%67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/24352API
curl https://kongchang.com/api/v1/knowledge/claims/24352MCP
get_claim(id=24352)