DeepSeek V4 Flash (Non-reasoning)

Benchmark scores, pricing, speed and comparisons for DeepSeek V4 Flash (Non-reasoning).

DeepSeek V4 Flash (Non-reasoning) is an AI model from DeepSeek, released 2026-04-24. It scores 18.9 on the Intelligence Index.

DeepSeek V4 Flash (Non-reasoning) at a glance

DeepSeek released DeepSeek V4 Flash (Non-reasoning) on April 24, 2026. It is marked as retired in the catalogue, so treat its numbers as a historical record.

DeepSeek V4 Flash (Non-reasoning) scores 18.9 on the Intelligence Index, the overall score the AI Benchmark rankings sort models by. Of its 6 individual benchmark results, the highest is 94.4% on TAU2 and the lowest is 7.8% on HLE. These scores come from independent third-party model evaluations, which Franklin AI syncs automatically each day.

It costs $0.09 per million input tokens and $0.20 per million output tokens, so a sample workload of 1 million input tokens and 200,000 output tokens costs about $0.13.

The benchmark data has no Coding Index, Math Index or speed measurement for DeepSeek V4 Flash (Non-reasoning) yet.

Every pair of models in the catalogue has a head-to-head page. Pick DeepSeek V4 Flash (Non-reasoning) and a rival on the model comparisons page to compare their scores, prices and speed side by side.

Key scores

Intelligence18.9Index score
Blended Cost$0.12Per 1M tokens

How does DeepSeek V4 Flash (Non-reasoning) score on each benchmark?

6 benchmark results for DeepSeek V4 Flash (Non-reasoning).

TAU2 Other
94.4%
GPQA Reasoning
71.6%
IFBench Other
47.2%
LCR Other
41.7%
TerminalBench Hard Other
34.1%
HLE Other
7.8%