A user says Grok 4.7 beat GPT-6.1 Sol, Opus 5.5 and GPT-6 Astra at every effort level on Frontier v4.
A user says they may have underestimated Grok 4.7, calling it “a very good model.” They claim it scored highest on Frontier v4, beating GPT-6.1 Sol, Opus 5.5 and GPT-6 Astra at every effort level.
7.7M
3 Sources, first seen ago
Many accounts praised Grok 4.7 for topping Frontier v4 benchmarks and showing strong innovation, while others dismissed it as unusable for real software engineering work due to frequent errors and incomplete results.
Based on 385 sentiment-bearing replies from 338 accounts across 2 conversations.
Many accounts praised Grok 4.7 for topping Frontier v4 benchmarks and showing strong innovation, while others dismissed it as unusable for real software engineering work due to frequent errors and incomplete results.
Based on 385 sentiment-bearing replies from 338 accounts across 2 conversations.
—
Not ranked yet
—
Not ranked yet
