AI Benchmark Model
DeepSeek V4.1 Flash (Reasoning, Max Effort)
Benchmark scores, pricing, speed, and model comparisons for DeepSeek V4.1 Flash (Reasoning, Max Effort).
Key scores
DeepSeek V4.1 Flash (Reasoning, Max Effort) is an artificial intelligence model released by DeepSeek on September 10, 2026. This model achieves an intelligence index score of 39.5 and demonstrates performance across several standardized evaluations, including an HLE score of 0.392, a SciCode score of 0.519, and an LCR score of 0.84. Regarding operational efficiency, the model provides an output speed of 267.06 tokens per second with a time to first token of 0.896 seconds. Pricing for the model is structured at $0.30 per 1 million input tokens and $1.20 per 1 million output tokens, resulting in a blended rate of $0.53 per 1 million tokens for users.
Benchmark results
3 tracked benchmark rows for DeepSeek V4.1 Flash (Reasoning, Max Effort).
LCR Other
84.0% SciCode Other
51.9% HLE Other
39.2%