TestingCatalog· 17 days agoSpaceXAI releases Grok 4.7 for coding and knowledge work
SpaceXAI launches Grok 4.7 for coding and knowledge work
New model
SpaceXAI released Grok 4.7, a model for coding and knowledge work, with access via Cursor, Grok Build, the Grok API, third-party coding harnesses, model routers, and cloud platforms.
It is trained on a new, larger base model with a longer reinforcement learning cycle and a harder task mix, and includes an entirely new safeguard stack.
Benchmark scores show gains over Grok 4.6 on several coding and professional benchmarks, though it trails GPT-5.6 Sol Max and Fable 5.1 Max on HealthBench Professional.
From the source
Grok 4.7 scored 46.3% on CursorBench 4.0, up from 40.4%, and reached 71.0% on DeepSWE v1.1 at high effort. It also posted 64.0% on EEBench, 1,657 on AA Briefcase v1.1, 38.0% on Terminal-Bench 4.0, and 19.6% on the Harvey Legal Agent Benchmark. Its 56.7% HealthBench Professional score trailed GPT-5.6 Sol Max and Fable 5.1 Max, showing that its lead is not universal.
testingcatalog.com