Head-to-head
DeepSeek V3 (Thinking) vs GPT-5.2
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)
DeepSeekGPT-5.2
OpenAI| Benchmark | DeepSeek V3 (Thinking) | GPT-5.2 |
|---|---|---|
Chatbot Arena Elo Arena | ||
SWE-bench Verified SWE-bench | — | |
Rolling Contamination-Controlled Average Rolling Avg | — | |
Rolling Data Analysis Data Analysis | — | |
FrontierMath Tiers 1-3 FrontierMath | — | |
SimpleQA Verified SimpleQA | — | |
OTIS Mock AIME 2024-2025 OTIS AIME | — | |
Humanity's Last Exam HLE | — | |
ARC-AGI 2 ARC-AGI 2 | — | |
Aider Polyglot Aider | — | |
Terminal-Bench 2 TermBench 2 | — | |
Frontier Composite Frontier | ||
Output Stability Stability | — | |
Format Adherence Format | — | |
Recovery Rate Recovery | — | |
Safety Handling Safety | — |
Methodology matches the main AI Model Analyzer About page.