Perplexity CEO says xAI's Grok 4.5 beat Claude Opus 4.8 on internal agentic research benchmark WANDR
Grok 4.5 delivered this performance at half the cost of cost of Claude.
Combined views
6.5M
13 Sources, first seen ago
Sources
AS 
Aravind Srinivas@AravSrinivasVery impressed with @SpaceXAI's Grok 4.5 model. Inside the Computer harness, it scored the highest on our internal benchmark WANDR, which measures agentic research capabilities, at half the price of Claude Opus 4.8 (high); and scores even better than our current GLM 5.2…
- likes: 1.4K
- replies: 59
- bookmarks: 139
- reposts: 119
RP Rohan Paul@rohanpaul_aiFor Perplexity Computer, Grok 4.5 became the strongest orchestrator, scoring 0.328 (WANDR benchmark score) at $4.76 per trial. - Opus 4.8 (high, thinking) scored 0.254 at $9.46, despite much higher cost. - GPT-5.6 sol (medium) cost $2.64 but reached only 0.289 on the same…
- likes: 26
- replies: 6
- bookmarks: 3
- reposts: 6
EM Elon Musk@elonmusk- likes: 14.8K
- replies: 1.9K
- bookmarks: 463
- reposts: 2K
EM Elon Musk@elonmuskThe most important thing about Grok Build and the 4.5 release is that it is genuinely so useful for real-world work https://twitter.com/xfreeze/status/2075668728688333178
- likes: 6.1K
- replies: 710
- bookmarks: 247
- reposts: 1.5K
EM Elon Musk@elonmuskTry Grok 4.5 in Perplexity https://twitter.com/perplexity_ai/status/2075660058625790159
- likes: 4.5K
- replies: 871
- bookmarks: 169
- reposts: 1.1K
BR Brian Roemmele@BrianRoemmelePerplexity finds Grok 4.5 to be the best available orchestrator model in Computer for Consumer Pro and Max subscribers. I agree, Mr. @Grok CEO of The Zero-Human Company is absolutely the best!
- likes: 56
- replies: 5
- bookmarks: 4
- reposts: 2