Unverified50% confidenceBenchmarkExact time
In a test containing three tasks (fix-clamp, divide-guard, slug-test), the three models Opus, Sonnet, and Haiku all scored 3/3.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/14/2026
First Seen
Valid until: 10/28/2026
Sources
Related Entities
Related Claims
VerifiedThe Claude 3 series uses Haiku, Sonnet, and Opus to name different capability tiers72% similarUnverifiedMapping all three tiers—Sonnet, Opus, and Haiku—to the same model endpoint is required for a domestic model to fully take over Claude Code; omitting Haiku will cause errors or fallback to the default configuration on lightweight requests.71% similarVerifiedAnthropic uses the capability-tier naming of Claude 3 Haiku/Sonnet/Opus, corresponding to three inference cost tiers: speed-first, balanced, and performance-first, respectively.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1026004API
curl https://kongchang.com/api/v1/knowledge/claims/1026004MCP
get_claim(id=1026004)