41x the recorded cost for 1.7 extra points - Grok 4.7 (high) vs DeepSeek V4.1 Flash (low) on BU Bench v2 👀
W open source this time.
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.
顯示更多
