Models
NaiveAI's Naive-N0.5-Flash: a speed-focused open-weights coding model, reviewed
Latent reviewed NaiveAI's Naive-N0.5-Flash, an open-weights coding model derived from Xiaomi's MiMo-V2.5 and paired with the company's NaiveRT inference engine. NaiveAI claims peak throughput around 2,100 tokens/s and sustained decode near 1,000 tokens/s, with target pricing of $0.10 per million input tokens and $0.40 per million output tokens. In Latent's small tests, the model answered faster at the median than DeepSeek V4.1 Flash 1017 and GLM 5.3 Flash at high thinking settings but used far more tokens on hard questions, while its reported coding benchmarks landed between the two comparison models.
NaiveAIopen-weight modelsAI coding