TAU2
Measured May 14, 2026Source
Score
0.34
Models13 4 0 
DeepSeek V3.2 Exp (Non-reasoning)
DeepSeekDeepSeekChina
This is an experimental version of the DeepSeek V3 series, optimized for general-purpose tasks and fast response times. It maintains strong code generation and long-context processing capabilities while operating in a non-reasoning mode for quicker outputs.
CodingFastCheapLong context
Input / 1M tokens
$0.275Output / 1M tokens
$0.415Supported plans
0Benchmark history
Evaluations
Terminalbench Hard
Measured May 14, 2026Source
Score
0.25
Lcr
Measured May 14, 2026Source
Score
0.43
Ifbench
Measured May 14, 2026Source
Score
0.43
Aime 25
Measured May 14, 2026Source
Score
0.58
Scicode
Measured May 14, 2026Source
Score
0.4
Livecodebench
Measured May 14, 2026Source
Score
0.55
Hle
Measured May 14, 2026Source
Score
0.09
Gpqa
Measured May 14, 2026Source
Score
0.74
Mmlu Pro
Measured May 14, 2026Source
Score
0.84
Artificial Analysis Math Index
Measured May 14, 2026Source
Score
57.7
Artificial Analysis Coding Index
Measured May 14, 2026Source
Score
30
Artificial Analysis Intelligence Index
Measured May 14, 2026Source
Score
28.4
CODPL speed
Provider ranking
百度云(千帆)
Product: 百度千帆 Coding Plan32.15
1,030 ms
100%
3
1h
Rank #4
Ollama Cloud
Product: Ollama Cloud45.43
1,501 ms
100%
2
1h
Rank #3
41.26
962 ms
100%
3
1h
Rank #2
61.91
733 ms
100%
3
1h
Rank #1
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