TAU2
Measured May 14, 2026Source
Score
0.91
Models13 4 1 
DeepSeek V3.2 (Reasoning)
DeepSeekDeepSeekChina
DeepSeek V3.2 (Reasoning) is a large language model optimized for complex reasoning tasks. It features an enhanced thinking mode or chain-of-thought capability, excelling in multi-step logical deduction, mathematical problem-solving, and code generation.
ReasoningCodingLong context
Input / 1M tokens
$0.30Output / 1M tokens
$0.45Supported plans
2Benchmark history
Evaluations
Terminalbench Hard
Measured May 14, 2026Source
Score
0.36
Lcr
Measured May 14, 2026Source
Score
0.65
Ifbench
Measured May 14, 2026Source
Score
0.61
Aime 25
Measured May 14, 2026Source
Score
0.92
Scicode
Measured May 14, 2026Source
Score
0.39
Livecodebench
Measured May 14, 2026Source
Score
0.86
Hle
Measured May 14, 2026Source
Score
0.22
Gpqa
Measured May 14, 2026Source
Score
0.84
Mmlu Pro
Measured May 14, 2026Source
Score
0.86
Artificial Analysis Math Index
Measured May 14, 2026Source
Score
92
Artificial Analysis Coding Index
Measured May 14, 2026Source
Score
36.7
Artificial Analysis Intelligence Index
Measured May 14, 2026Source
Score
41.7
CODPL speed
Provider ranking
Ollama Cloud
Product: Ollama Cloud45.43
1,501 ms
100%
2
1h
Rank #3
61.91
733 ms
100%
3
1h
Rank #1
41.26
962 ms
100%
3
1h
Rank #2
百度云(千帆)
Product: 百度千帆 Coding Plan32.15
1,030 ms
100%
3
1h
Rank #4
Plan availability
Products and plans that support this model
Infini Coding Plan
Infini Coding Plan
Infini Coding Plan is a subscription-based AI coding service from Infinigence AI that provides access to multiple large language models from providers like DeepSeek, MiniMax, Kimi, and GLM for use in integrated coding tools such as Claude Code and Cursor, with tiered request-based pricing.
Discussion
Thinking... Make sure you are connected to GitHub server