DeepSeek V4.1 Flash scores 45 on Artificial Analysis Intelligence Index
DeepSeek v4.1 Flash 1017 scores 45 in Artificial Analysis
Artificial Analysis benchmarks DeepSeek V4.1 Flash (max) on its Intelligence Index v4.3.2, which aggregates ten evaluations including Terminal-Bench 4.0, SciCode, Humanity's Last Exam, and AA-Omniscience. The model earns a score of 45. The analysis also covers cost per task, output speed, latency, context window, and token usage, with no publicly available API listed for the model.
AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer.