TAU2
Measured Jul 10, 2026Source
Score
0.94
Models11 0 
DeepSeek V4 Flash (Non-reasoning)
DeepSeekDeepSeekChina
A fast and efficient model from the DeepSeek V4 family, optimized for low-latency responses and general tasks. It excels in code generation and instruction following, but is not designed for complex reasoning or chain-of-thought tasks.
FastCoding
Input / 1M tokens
$0.14Output / 1M tokens
$0.28Output tokens/s
105First-token seconds
0.88sSupported plans
0Benchmark history
Evaluations
Terminalbench Hard
Measured Jul 10, 2026Source
Score
0.34
Lcr
Measured Jul 10, 2026Source
Score
0.33
Ifbench
Measured Jul 10, 2026Source
Score
0.47
Scicode
Measured Jul 10, 2026Source
Score
0.37
Hle
Measured Jul 10, 2026Source
Score
0.07
Gpqa
Measured Jul 10, 2026Source
Score
0.72
Artificial Analysis Intelligence Index
Measured Jul 10, 2026Source
Score
28.7
Tau Banking
Measured Jul 10, 2026Source
Score
0.23
Terminalbench V2 1
Measured Jul 10, 2026Source
Score
0.62
Artificial Analysis Coding Index
Measured Jul 10, 2026Source
Score
56.2
Plan availability
Products and plans that support this model
No products or plans have been linked to this model yet.
User ratings
Loading ratings...
Discussion
Thinking... Make sure you are connected to GitHub server