TAU2
Measured May 29, 2026Source
Score
0.37
Models13 0 
DeepSeek V3.1 (Reasoning)
DeepSeekDeepSeekChina
DeepSeek V3.1 (Reasoning) is a specialized variant of the V3.1 model optimized for complex reasoning tasks. It incorporates an enhanced thinking process to deliver more accurate and logical solutions for problems requiring multi-step analysis.
ReasoningCodingCheap
Input / 1M tokens
$0.59Output / 1M tokens
$1.69Supported plans
0Benchmark history
Evaluations
Terminalbench Hard
Measured May 29, 2026Source
Score
0.25
Lcr
Measured May 29, 2026Source
Score
0.53
Ifbench
Measured May 29, 2026Source
Score
0.42
Aime 25
Measured May 29, 2026Source
Score
0.9
Scicode
Measured May 29, 2026Source
Score
0.39
Livecodebench
Measured May 29, 2026Source
Score
0.78
Hle
Measured May 29, 2026Source
Score
0.13
Gpqa
Measured May 29, 2026Source
Score
0.78
Mmlu Pro
Measured May 29, 2026Source
Score
0.85
Artificial Analysis Math Index
Measured May 29, 2026Source
Score
89.7
Artificial Analysis Coding Index
Measured May 29, 2026Source
Score
29.7
Artificial Analysis Intelligence Index
Measured May 29, 2026Source
Score
27.7
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