AI Benchmark Model
DeepSeek V4.1 Flash (Non-Reasoning)
Benchmark scores, pricing, speed, and model comparisons for DeepSeek V4.1 Flash (Non-Reasoning).
Key scores
DeepSeek V4.1 Flash (Non-Reasoning) is an artificial intelligence model developed by DeepSeek and released on September 10, 2026. This model features an intelligence index of 24.7 and has been evaluated across several standardized benchmarks, achieving an HLE score of 0.108, a SciCode score of 0.355, and an LCR score of 0.553333333333333. In terms of operational performance, the model provides an output speed of 203.209 tokens per second with a time to first token of 0.79 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 cost of $0.53 per 1 million tokens for users.
Benchmark results
3 tracked benchmark rows for DeepSeek V4.1 Flash (Non-Reasoning).
LCR Other
55.3% SciCode Other
35.5% HLE Other
10.8%