DeepSeek V3.2-Exp Benchmark Details
DeepSeek V3.2-Exp currently shows benchmark results led by SimpleQA (1 / 45, score 97.10), MMLU Pro (23 / 124, score 85), Aider-Polyglot (7 / 26, score 74.50).
Benchmark Results
DeepSeek V3.2-Exp
Benchmark Results
综合评估
9 evaluationsBenchmark / mode
Score
Rank/total
编程与软件工程
3 evaluationsBenchmark / mode
Score
Rank/total
AI Agent - 工具使用
2 evaluationsBenchmark / mode
Score
Rank/total
Agent能力评测
4 evaluationsBenchmark / mode
Score
Rank/total