Head-to-head
DeepSeek V3 (Thinking) vs o3-mini
Normalized scores are min-maxed per benchmark across all models we track (0–100). Open the interactive compare view to add benchmarks to the radar chart or pull in more models.
DeepSeek V3 (Thinking)
DeepSeeko3-mini
OpenAI| Benchmark | DeepSeek V3 (Thinking) | o3-mini |
|---|---|---|
Chatbot Arena Elo Arena | ||
AIME 2024 AIME | — | |
HumanEval HumanEval | — | |
LiveCodeBench LiveCB | — | |
SWE-bench Verified SWE-bench | — | |
MMMU MMMU | — | |
MathVista MathVista | — | |
RULER 128k RULER | — | |
Output Speed Speed | — | |
Time to First Token TTFT | — | |
Rolling Contamination-Controlled Average Rolling Avg | — | |
Rolling Data Analysis Data Analysis | — | |
FrontierMath Tiers 1-3 FrontierMath | — | |
OTIS Mock AIME 2024-2025 OTIS AIME | — | |
ARC-AGI 2 ARC-AGI 2 | — | |
Aider Polyglot Aider | ||
Frontier Composite Frontier |
Methodology matches the main AI Model Analyzer About page.