Many users praise Grok 4.5 for delivering top real-world coding speed and value on the FrontierCode leaderboard while others mock the charts as flawed or dismiss the claims outright.
Based on 248 visible X reactions from 1014 accounts.
Ask a question below.
Published answers will appear here.
The chart features a controversial backward horizontal axis for output tokens.
@elonmusk GROK SUCKS! Rips off users by making them invisible to public. AI Cheaters!
@cognition Code you'd actually merge is a much better bar than most benchmarks use.
@elonmusk 4.5 is actually a beast. tok/s? mind blowing
@BitBrew1 @scaling01 What kind of insane cope is even this
@elonmusk GROK is the best
The FrontierCode leaderboard is now live: a dedicated page that tracks which models are writing code you’d actually merge. All scores — including Grok 4.5 and Inkling — are available, along with full methodology and sample tasks.
it's actually hilarious and sad that Anthropic who were once the goats of reasoning efficiency are now just slop-maxxing big fan of whatever OpenAI is doing
FrontierCode by Cognition now has a live leaderboard btw https://cognition.com/frontiercode
Grok has the best value for coding
@inductionheads don't ask me I think it's fine that top right is better
See the scores: https://cognition.com/frontiercode
@scaling01 Why do the put the x axis backwards again
Many users praise Grok 4.5 for delivering top real-world coding speed and value on the FrontierCode leaderboard while others mock the charts as flawed or dismiss the claims outright.
Based on 248 visible X reactions from 1014 accounts.
Ask a question below.
Published answers will appear here.