← All models
Compare

DeepSeek-V3.2 vs GPT-5.5

DeepSeek-V3.2 (DeepSeek) and GPT-5.5 (OpenAI) compared on benchmarks, pricing, context window, and use-case rankings.

DeepSeek-V3.2DeepSeek · 1 in the newsGPT-5.5OpenAI · 14 in the news
Scores
Intelligence (ECI)146159
Coding2789
Math3697
Reasoning & Knowledge2691
Agentic & Tools2995
Specifications
DeveloperDeepSeekOpenAI
FamilyDeepSeekGPT
ReleasedDec 1, 2025Apr 23, 2026
Parameters
AvailabilityOpen weights (unrestricted)API access
Context window131K1.1M
Price — $/M input$0.23$5.00
Price — $/M output$0.34$30.00
Inputstextfile, image, text
Outputstexttext
Benchmarks
AIME 2024/202588%100%
APEX7%38%
ARC-AGI57%95%
ARC-AGI-24%85%
FrontierMath22%52%
FrontierMath Tier 42%35%
GPQA Diamond83%94%
SimpleBench53%69%
SimpleQA Verified28%63%
Terminal-Bench40%85%
WebDev Arena12861505
WeirdML47%85%
GSO (code optimization)40%
SWE-bench Verified81%

Use-case scores are 0–100 percentile composites across each area’s benchmarks, ranked against every model from the past year. Highlighted cells lead each row. Open a model for the full picture.

Frequently asked questions

Is DeepSeek-V3.2 better than GPT-5.5?

On Epoch AI's Capabilities Index, GPT-5.5 scores higher (159) than DeepSeek-V3.2 (146). The right pick depends on your task — compare their coding, math, and reasoning scores in the table above.

Which is cheaper, DeepSeek-V3.2 or GPT-5.5?

DeepSeek-V3.2 is cheaper on input tokens at $0.23 per million, versus $5.00 (representative OpenRouter pricing).

Which has a larger context window, DeepSeek-V3.2 or GPT-5.5?

GPT-5.5 supports up to 1.1M tokens, compared with 131K for the other.

Which is better for coding, DeepSeek-V3.2 or GPT-5.5?

Across coding benchmarks like SWE-bench Verified and Terminal-Bench, GPT-5.5 ranks higher — 89th vs 27th percentile among the models tracked on Model Beat.

Want a different match-up? Open the compare tool to add or swap models.

Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.