Compare · ModelsLive · 2 picked · head to head

DeepSeek V3.2 Exp vs GPT-5

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

Winner summary

GPT-5 wins 5 of 5 shared benchmarks. Leads in coding · general · knowledge.

Category leads
coding·GPT-5general·GPT-5knowledge·GPT-5

Head to head · from the data · data as of 2026-11-15

  • Benchmarks · DeepSeek V3.2 Exp leads on 0 of 5 shared benchmarks, GPT-5 on 5 (Aider polyglot, Dtbench, Fiction.LiveBench, Lmca, 1 more)
  • Price · DeepSeek V3.2 Exp input $0.27/M vs GPT-5 $1.25/M, DeepSeek V3.2 Exp is 78% cheaper (OpenRouter list price, as of 2026-11-15)
  • Cheapest provider · DeepSeek V3.2 Exp at SiliconFlow $0.27/M input (1 offer) as of 2026-11-15 · GPT-5 at Azure and 1 other provider $1.25/M input (of 3 offers) as of 2026-11-15
  • Context · DeepSeek V3.2 Exp 164K tokens vs GPT-5 400K tokens
  • Released · DeepSeek V3.2 Exp Sep 29, 2025 vs GPT-5 Aug 7, 2025 · 1 month apart
  • Open weights · DeepSeek V3.2 Exp has open weights (on Hugging Face as deepseek-ai/DeepSeek-V3.2-Exp)
  • Price history · DeepSeek V3.2 Exp OpenRouter input list price moved once by 5% or more in the 90 days to 2026-11-15 · GPT-5 OpenRouter input list price had no move of 5% or more in the 90 days to 2026-11-15

Sources · scores from public leaderboards, list prices and provider offers from OpenRouter, price moves from the BenchGecko changelog (5% or more, held in the next daily check), Gecko tests run by BenchGecko.

Hype vs Reality
DeepSeek V3.2 Exp
#148 by perf·no signal
QUIET
GPT-5
#115 by perf·#10 by attention
DESERVED
Best value
15.4x better value than GPT-5
DeepSeek V3.2 Exp
142.4 pts/$
$0.34/M
GPT-5
9.3 pts/$
$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 V3.2 ExpGPT-5
Aider polyglot
GPT-5 leads by +13.8
Aider Polyglot · measures how well AI models can edit code across multiple programming languages using the Aider coding assistant framework.
DeepSeek V3.2 Exp
74.2
GPT-5
88.0
Dtbench
GPT-5 leads by +4.9
DeepSeek V3.2 Exp
79.5
GPT-5
84.5
Fiction.LiveBench
GPT-5 leads by +13.9
Fiction.LiveBench · a continuously updated benchmark using recently published fiction to test reading comprehension and reasoning, preventing data contamination.
DeepSeek V3.2 Exp
83.3
GPT-5
97.2
Lmca
GPT-5 leads by +12.8
DeepSeek V3.2 Exp
34.3
GPT-5
47.0
WeirdML
GPT-5 leads by +21.2
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
DeepSeek V3.2 Exp
39.5
GPT-5
60.7
Full benchmark table
BenchmarkDeepSeek V3.2 ExpGPT-5
Aider polyglot
Aider Polyglot · measures how well AI models can edit code across multiple programming languages using the Aider coding assistant framework.
74.288.0
Dtbench
79.584.5
Fiction.LiveBench
Fiction.LiveBench · a continuously updated benchmark using recently published fiction to test reading comprehension and reasoning, preventing data contamination.
83.397.2
Lmca
34.347.0
WeirdML
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
39.560.7
Pricing · per 1M tokens · projected $/mo at 10M tokens
ModelInputOutputContextProjected $/mo
DeepSeek logoDeepSeek V3.2 Exp$0.27$0.41164K tokens (~82 books)$3.05
OpenAI logoGPT-5$1.25$10.00400K tokens (~200 books)$34.38
DeepSeek V3.2 Exp leads on 0 of 5 shared benchmarks, GPT-5 on 5 (Aider polyglot, Dtbench, Fiction.LiveBench, Lmca, 1 more)