DeepSeek-V3.2 (Thinking) vs K-EXAONE-236B-A23B: Specs & Benchmark Comparison

CharacteristicDeepSeek-V3.2 (Thinking)K-EXAONE-236B-A23B
CompanyDeepSeekLG AI Research
Release DateNovember 30, 2025December 30, 2025
Parameters685B236B
MultimodalNoNo
Context (input)131K33K
Context (output)66K33K
Input Price / 1M$0.28$0.60
Output Price / 1M$0.42$1.00
Average Score0.90.8
Benchmarks
T2-Bench0.80.7
MMLU-Pro0.80.8
AIME 20250.90.9

Visual Benchmark Comparison

DeepSeek-V3.2 (Thinking)
K-EXAONE-236B-A23B
T2-Bench0.8 vs 0.7
0.8
0.7
MMLU-Pro0.8 vs 0.8
0.8
0.8
AIME 20250.9 vs 0.9
0.9
0.9

Verdict

DeepSeek-V3.2 (Thinking) leads in 2 out of 4 comparison categories.

Overall Performance

Both models show comparable average scores: DeepSeek-V3.2 (Thinking) — 0.9, K-EXAONE-236B-A23B — 0.8.

API Cost

DeepSeek-V3.2 (Thinking) is 2.3x cheaper: input $0.28/1M vs $0.60/1M tokens.

Context Window

DeepSeek-V3.2 (Thinking) supports a larger context: 131K vs 33K tokens.

Recency

K-EXAONE-236B-A23B is newer: released 12/30/2025 vs 11/30/2025.

More About These Models

Related Comparisons

The DeepSeek-V3.2 (Thinking) and K-EXAONE-236B-A23B 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 K-EXAONE-236B-A23B page. See also the complete list of AI model comparisons.