Same prompt: Haiku 5.5 finishes in 27 min for $0.8 while Grok 4.7 takes 35 min and $4.1
iamfakhrealam · x · 2026-10-08
notjazii tested Haiku 5.5 and Grok 4.7 on the same prompt at max reasoning: Haiku took 27 minutes and $0.8 in Claude Code; Grok took 35 minutes and $4.1 in Grok Build.
The author was "really impressed by what Haiku did and literally mogged Grok 4.7." A concrete third-party benchmark worth referencing for model choice.
More from Models
- Ultrafast access limited to Pro 500, Enterprise and Edu plans; EU data residency added — OpenAIDevs · 2026-10-09
- OpenAI prices GPT-6.1 Sol Ultrafast at $12/M input and $60/M output tokens — OpenAIDevs · 2026-10-09
- OpenAI rolls out Ultrafast mode for GPT-6.1 Sol at up to 8x standard speed — OpenAIDevs · 2026-10-09
- Haiku 5.5 Hits 85% Success on Robot Tasks at Under $0.02 Per Attempt — scaling01 · 2026-10-09
- LangChain Podcast Digs Into Decision Models as OpenAI and Databricks Enter the Space — LangChain · 2026-10-09
- Plot Twist: OpenAI Retracts Its Hodge Conjecture Result — rickasaurus · 2026-10-09