Unverified50% confidenceBenchmarkExact time
Haiku 5.5 outperforms GPT-6 Luna by approximately 40% on Computer Use tasks.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/9/2026
First Seen
Valid until: 1/7/2027
Sources
Related Entities
Related Claims
UnverifiedHaiku 5.5's score on computer use tasks jumped from 16% to 72%77% similarUnverifiedUnder high-reasoning-intensity settings such as max, Haiku 5.5's token consumption increases significantly, and the per-task cost may be less economical than GPT-6 Luna.73% similarUnverifiedHaiku 5.5 shows a notable capability leap between different reasoning intensity levels, with a considerable improvement from high to max/X-high, unlike Opus 5.5 or Sonnet.70% similarUnverifiedKey parameters of Haiku 5.5 such as specific performance benchmarks, pricing details, and context window size have not yet been disclosed in publicly available information70% similarUnverifiedIn Databricks' OfficeQA Pro V1 evaluation, Claude Haiku 5.5 achieved approximately 15% quality improvement over the previous generation Haiku 4.5, while costing only a fraction of the latter.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/990911API
curl https://kongchang.com/api/v1/knowledge/claims/990911MCP
get_claim(id=990911)