Our browser benchmark looks suspiciously like my coding preferences.
I LOVE Astra. DeepSeek V4.1 Flash is my go-to for uncensored coding.
Feels like long browser tasks reveal more than just browser ability ๐
๋ ๋ณด๊ธฐ
Grok 4.7 just dropped. Still chasing DeepSeek ๐
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.
๋ ๋ณด๊ธฐ
