gpt-6IMAGE
Long Horizon browser benchmark: Astra scores 80.6, Grok 4.7 only 39.9
On Browser Use's Long Horizon v2 benchmark, Grok 4.7 improves over 4.6 but still scores less than half of Astra's 80.6, with DeepSeek V4.1 Flash in between.
Browser Use
@browser_useArchived 2026.09.22Originally posted 2026.09.22
Browser Use @browser_useOriginally posted 2026.09.22
Grok 4.7 just dropped. Still chasing DeepSeek 👀 Long Horizon Browser Use Benchmark v2 > GPT-6 Astra: 80.6 > DeepSeek V4.1 Flash: 47.9 > Grok 4.7: 39.9 > Grok 4.6: 31.2 Better than 4.6. Still less than half Astra's score.
x.com/browser_use/status/2102139299630338067Archived 2026.09.22 10:17