TAU2
Measured May 14, 2026Source
Score
0.94
Models9 2 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
91.21First-token seconds
0.83sSupported plans
0Benchmark history
Evaluations
Terminalbench Hard
Measured May 14, 2026Source
Score
0.34
Lcr
Measured May 14, 2026Source
Score
0.33
Ifbench
Measured May 14, 2026Source
Score
0.47
Scicode
Measured May 14, 2026Source
Score
0.37
Hle
Measured May 14, 2026Source
Score
0.07
Gpqa
Measured May 14, 2026Source
Score
0.72
Artificial Analysis Coding Index
Measured May 14, 2026Source
Score
35.2
Artificial Analysis Intelligence Index
Measured May 14, 2026Source
Score
36.5
CODPL speed
Provider ranking
96.84
754 ms
100%
3
1h
Rank #1
Ollama Cloud
Product: Ollama Cloud83.57
997.5 ms
100%
2
1h
Rank #2
Plan availability
Products and plans that support this model
No products or plans have been linked to this model yet.
Discussion
Thinking... Make sure you are connected to GitHub server