Android Bench adds Kimi K3.1 Pro and DeepSeek V4.1 Flash results
AI summary
Google’s Android Developers account published Android Bench results for GPT-6.1 Terra, Kimi K3.1 Pro and DeepSeek V4.1 Flash, according to IT之家. With kimi-code, Kimi K3.1 Pro recorded a 24.0% pass rate and 82.3% average completion across 30 long-horizon tasks, taking 27.4 hours and costing US$317.4 per run. DeepSeek V4.1 Flash, evaluated with opencode, recorded a 17.3% pass rate and 71.2% average completion, with a 12.0-hour average completion time and US$9.9 run cost.
In-depth insight
The results provide Android development teams with a shared comparison of coding-model performance, completion time and benchmark cost on long-horizon engineering tasks.