@rohanpaul_ai: Legal work saw one of Grok 4.7’s biggest jumps. On the Harvey Legal Agent Benchmark, Grok 4.7 scored 19.6%, while GPT-5…
Summary
Grok 4.7 shows significant improvements in legal work and terminal tasks, outperforming competitors on benchmarks like Harvey Legal Agent Benchmark and Terminal-Bench 4.0, while keeping token prices unchanged.
View Cached Full Text
Cached at: 09/22/26, 03:39 AM
Legal work saw one of Grok 4.7’s biggest jumps.
On the Harvey Legal Agent Benchmark, Grok 4.7 scored 19.6%, while GPT-5.6 Sol Max scored 2.5% and Fable 5.1 Max scored 6.7%
Also, Long-running terminal work nearly doubled. Grok 4.7 reached 38.0% on Terminal-Bench 4.0, versus 20.3% for Grok 4.6, suggesting the larger improvement is in agents that must keep working through extended computer tasks.
And SpaceXAI made those gains without raising the headline token price. Grok 4.7 remains at 2/6 per 1M input/output tokens.
SpaceXAI (@SpaceXAI): Grok 4.7 is here.
It’s a notable improvement over Grok 4.6 at the same price and speed.
Similar Articles
@elonmusk: Grok 4.7 ranks first in legal matters
Grok 4.7 ranks first on the updated Harvey LAB-AA v1.1 legal agent benchmark, which introduces hallucination checks and stricter accuracy standards. The benchmark was revised by Artificial Analysis in collaboration with Harvey to improve evaluation rigor.
Grok 4.7 benchmarks
This article likely discusses the benchmark results for the Grok 4.7 AI model, comparing its performance across various tasks.
@rohanpaul_ai: Grok 4.6 beat GPT-5.6 Sol on agentic loop efficiency, spending $13.11 versus $20.18 across the same 3 builds. Grok 4.6'…
The article reports an experiment comparing Grok 4.6 and GPT-5.6 Sol on agentic loop efficiency for coding tasks, showing Grok 4.6 is more cost-effective with fewer model calls and effective prompt caching.
@elonmusk: Grok 4.6 is #1 on healthcare questions
Grok 4.6 has achieved the top position on MedAgentBench, outperforming GPT-5.6 Sol and Grok 4.5 in real-world healthcare AI tasks.
@elonmusk: Grok 4.5 is excellent for real-world work
Elon Musk endorses Grok 4.5 for real-world tasks, citing a Ramp test where Grok achieved the highest perfect-extraction rate on 150k business invoices.