Compare · ModelsLive · 2 picked · head to head

DeepSeek V3.2 vs GPT-5.1

Side by side · benchmarks, pricing, and signals you can act on.

Winner summary

GPT-5.1 wins 11 of 11 shared benchmarks. Leads in reasoning · arena · knowledge.

Category leads
reasoning·GPT-5.1arena·GPT-5.1knowledge·GPT-5.1math·GPT-5.1coding·GPT-5.1
Hype vs Reality
DeepSeek V3.2
#84 by perf·no signal
QUIET
GPT-5.1
#97 by perf·no signal
QUIET
Best value
19.1x better value than GPT-5.1
DeepSeek V3.2
168.3 pts/$
$0.32/M
GPT-5.1
8.8 pts/$
$5.63/M
Vendor risk
One or more vendors flagged
DeepSeek logo
DeepSeek
$3.4B·Tier 1
Higher risk
OpenAI logo
OpenAI
$840.0B·Tier 1
Medium risk
Head to head
DeepSeek V3.2GPT-5.1
ARC-AGI
GPT-5.1 leads by +15.8
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
DeepSeek V3.2
57.0
GPT-5.1
72.8
ARC-AGI-2
GPT-5.1 leads by +13.6
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
DeepSeek V3.2
4.0
GPT-5.1
17.6
Chatbot Arena Elo · Coding
GPT-5.1 leads by +11.9
DeepSeek V3.2
1326.9
GPT-5.1
1338.8
Chatbot Arena Elo · Overall
GPT-5.1 leads by +14.1
DeepSeek V3.2
1424.4
GPT-5.1
1438.5
Chess Puzzles
GPT-5.1 leads by +18.0
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
DeepSeek V3.2
14.0
GPT-5.1
32.0
FrontierMath-2025-02-28-Private
GPT-5.1 leads by +8.9
FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning.
DeepSeek V3.2
22.1
GPT-5.1
31.0
FrontierMath-Tier-4-2025-07-01-Private
GPT-5.1 leads by +10.4
FrontierMath Tier 4 (Jul 2025) · the most challenging tier of frontier mathematics, containing problems that push the absolute limits of AI mathematical reasoning.
DeepSeek V3.2
2.1
GPT-5.1
12.5
GPQA diamond
GPT-5.1 leads by +5.6
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
DeepSeek V3.2
77.9
GPT-5.1
83.5
OTIS Mock AIME 2024-2025
GPT-5.1 leads by +0.8
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
DeepSeek V3.2
87.8
GPT-5.1
88.6
SimpleQA Verified
GPT-5.1 leads by +21.4
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
DeepSeek V3.2
27.5
GPT-5.1
48.9
Terminal Bench
GPT-5.1 leads by +8.0
Terminal-Bench 2.0 · evaluates AI agents on real terminal-based coding tasks · writing scripts, debugging, running tests, and managing projects entirely through command-line interaction. Tests both code quality and terminal fluency. Claude Opus 4.7 scores 69.4%, demonstrating significant agentic terminal competence.
DeepSeek V3.2
39.6
GPT-5.1
47.6
Full benchmark table
BenchmarkDeepSeek V3.2GPT-5.1
ARC-AGI
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
57.072.8
ARC-AGI-2
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
4.017.6
Chatbot Arena Elo · Coding
1326.91338.8
Chatbot Arena Elo · Overall
1424.41438.5
Chess Puzzles
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
14.032.0
FrontierMath-2025-02-28-Private
FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning.
22.131.0
FrontierMath-Tier-4-2025-07-01-Private
FrontierMath Tier 4 (Jul 2025) · the most challenging tier of frontier mathematics, containing problems that push the absolute limits of AI mathematical reasoning.
2.112.5
GPQA diamond
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
77.983.5
OTIS Mock AIME 2024-2025
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
87.888.6
SimpleQA Verified
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
27.548.9
Terminal Bench
Terminal-Bench 2.0 · evaluates AI agents on real terminal-based coding tasks · writing scripts, debugging, running tests, and managing projects entirely through command-line interaction. Tests both code quality and terminal fluency. Claude Opus 4.7 scores 69.4%, demonstrating significant agentic terminal competence.
39.647.6
Pricing · per 1M tokens · projected $/mo at 10M tokens
ModelInputOutputContextProjected $/mo
DeepSeek logoDeepSeek V3.2$0.25$0.38131K tokens (~66 books)$2.83
OpenAI logoGPT-5.1$1.25$10.00400K tokens (~200 books)$34.38