DeepSeek V3.2vsDeepSeek-V3.1
Across 6 shared benchmarks, DeepSeek V3.2 leads overall: DeepSeek V3.2 wins 6, DeepSeek-V3.1 wins 0, with 0 ties and an average score difference of +15.92.
DeepSeek V3.2
DeepSeek-AI · 2025-12-01 · Reasoning model
DeepSeek-V3.1
DeepSeek-AI · 2025-08-20 · AI model
DeepSeek V3.26 wins(100%)(0%)0 winsDeepSeek-V3.1
Benchmark scores
Grouped by capability, sorted by largest gap within each. 6 shared benchmarks.
Coding and Software Engineer
DeepSeek V3.2 2/2| Benchmark | DeepSeek V3.2 | DeepSeek-V3.1 | Diff |
|---|---|---|---|
| LiveCodeBench | 83.3019 / 118Thinking (No Tools) | 56.4076 / 118 | +26.90 |
| SWE-bench Verified | 73.1040 / 103thinking + 使用工具 | 6665 / 103 | +7.10 |
General Knowledge
DeepSeek V3.2 2/2| Benchmark | DeepSeek V3.2 | DeepSeek-V3.1 |
|---|
Specs
| Field | DeepSeek V3.2 | DeepSeek-V3.1 |
|---|---|---|
| Publisher | DeepSeek-AI | DeepSeek-AI |
| Release date | 2025-12-01 | 2025-08-20 |
| Model type | Reasoning model | AI model |
| Architecture | MoE | MoE |
| Parameters | 6710.0 | 6710.0 |
| Context length | 128K | 128K |
| Max output | 8192 | 8192 |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | DeepSeek V3.2 | DeepSeek-V3.1 |
|---|---|---|
| Text input | Not public | 0.56 美元/100 万tokens |
| Text output | Not public | 1.68 美元/100 万tokens |
One or both models have incomplete public pricing.
Summary
- DeepSeek V3.2leads in:Coding and Software Engineer (2/2), General Knowledge (2/2), Agent Level Benchmark (1/1), Math and Reasoning (1/1)
On average across the 6 shared benchmarks, DeepSeek V3.2 scores 15.92 higher.
Largest single-benchmark gap: AIME2025 — DeepSeek V3.2 93.10 vs DeepSeek-V3.1 49.80 (+43.30).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.