Models

DeepSeek V3 0324

DeepSeek V3 0324 is DeepSeek's flagship model, featuring strong reasoning and coding capabilities. It offers a high-performance, cost-effective solution for complex tasks.

CodingReasoningFastCheap
Input / 1M tokens
$1.20
Output / 1M tokens
$1.25
Supported plans
6

Benchmark history

Evaluations

15

TAU2

Measured May 14, 2026Source

Score

0.47

Terminalbench Hard

Measured May 14, 2026Source

Score

0.15

Lcr

Measured May 14, 2026Source

Score

0.41

Ifbench

Measured May 14, 2026Source

Score

0.41

Aime 25

Measured May 14, 2026Source

Score

0.41

Aime

Measured May 14, 2026Source

Score

0.52

Math 500

Measured May 14, 2026Source

Score

0.94

Scicode

Measured May 14, 2026Source

Score

0.36

Livecodebench

Measured May 14, 2026Source

Score

0.41

Hle

Measured May 14, 2026Source

Score

0.05

Gpqa

Measured May 14, 2026Source

Score

0.66

Mmlu Pro

Measured May 14, 2026Source

Score

0.82

Artificial Analysis Math Index

Measured May 14, 2026Source

Score

41

Artificial Analysis Coding Index

Measured May 14, 2026Source

Score

22

Artificial Analysis Intelligence Index

Measured May 14, 2026Source

Score

22.3

Plan availability

Products and plans that support this model

2

Discussion

Thinking... Make sure you are connected to GitHub server