TAU2
Measured Jul 10, 2026Source
Score
0.34
Models15 0 
DeepSeek V3.2 Exp (Reasoning)
DeepSeekDeepSeekChina
An experimental reasoning-focused variant of the DeepSeek V3.2 model, optimized for complex logical deduction and chain-of-thought tasks. It likely maintains strong coding and general capabilities while enhancing performance on problems requiring multi-step reasoning.
ReasoningCodingFastCheap
Input / 1M tokens
$0.28Output / 1M tokens
$0.42Supported plans
0Benchmark history
Evaluations
Terminalbench Hard
Measured Jul 10, 2026Source
Score
0.31
Lcr
Measured Jul 10, 2026Source
Score
0.69
Ifbench
Measured Jul 10, 2026Source
Score
0.54
Aime 25
Measured Jul 10, 2026Source
Score
0.88
Scicode
Measured Jul 10, 2026Source
Score
0.38
Livecodebench
Measured Jul 10, 2026Source
Score
0.79
Hle
Measured Jul 10, 2026Source
Score
0.14
Gpqa
Measured Jul 10, 2026Source
Score
0.8
Mmlu Pro
Measured Jul 10, 2026Source
Score
0.85
Artificial Analysis Math Index
Measured Jul 10, 2026Source
Score
87.7
Artificial Analysis Intelligence Index
Measured Jul 10, 2026Source
Score
25.4
Tau Banking
Measured Jul 10, 2026Source
Score
0.19
Terminalbench V2 1
Measured Jul 10, 2026Source
Score
0.47
Artificial Analysis Coding Index
Measured Jul 10, 2026Source
Score
44.2
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