DeepSeek-V3.2 (Thinking) vs GPT-5.4: Specs & Benchmark Comparison

CharacteristicDeepSeek-V3.2 (Thinking)GPT-5.4
CompanyDeepSeekOpenAI
Release DateNovember 30, 2025March 5, 2026
Parameters685B
MultimodalNoYes
Context (input)131K1.0M
Context (output)66K128K
Input Price / 1M$0.28$2.50
Output Price / 1M$0.42$15.00
Average Score0.90.9
Benchmarks
GPQA0.80.9

Visual Benchmark Comparison

DeepSeek-V3.2 (Thinking)
GPT-5.4
GPQA0.8 vs 0.9
0.8
0.9

Verdict

GPT-5.4 leads in 2 out of 4 comparison categories.

Overall Performance

Both models show comparable average scores: DeepSeek-V3.2 (Thinking) — 0.9, GPT-5.4 — 0.9.

API Cost

DeepSeek-V3.2 (Thinking) is 25.0x cheaper: input $0.28/1M vs $2.50/1M tokens.

Context Window

GPT-5.4 supports a larger context: 1M vs 131K tokens.

Recency

GPT-5.4 is newer: released 3/5/2026 vs 11/30/2025.

More About These Models

Related Comparisons

The DeepSeek-V3.2 (Thinking) and GPT-5.4 comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the DeepSeek-V3.2 (Thinking) or GPT-5.4 page. See also the complete list of AI model comparisons.