DeepSeek V3.2vsDeepSeek-V3.1
Across 6 shared benchmarks, DeepSeek V3.2 leads overall: DeepSeek V3.2 wins 5, DeepSeek-V3.1 wins 1, with 0 ties and an average score difference of +15.60.
DeepSeek V3.2
DeepSeek-AI · 2025-12-01 · Reasoning model
DeepSeek-V3.1
DeepSeek-AI · 2025-08-20 · Chat model
DeepSeek V3.25 wins(83%)(17%)1 winDeepSeek-V3.1
Benchmark scores
Grouped by capability, sorted by largest gap within each. 6 shared benchmarks.
Coding and Software Engineer
DeepSeek V3.2 1/1| Benchmark | DeepSeek V3.2 | DeepSeek-V3.1 | Diff |
|---|---|---|---|
| LiveCodeBench | 59.30133 / 250Normal (No Tools) | 56.40145 / 250Normal (No Tools) | +2.90 |
General Evaluation
DeepSeek V3.2 1/1| Benchmark | DeepSeek V3.2 | DeepSeek-V3.1 | Diff |
|---|---|---|---|
| GPQA Diamond | 75.10279 / 462Normal (No Tools) | 74.90283 / 462Normal (No Tools) | +0.20 |
General Knowledge
DeepSeek V3.2 1/1| Benchmark | DeepSeek V3.2 | DeepSeek-V3.1 | Diff |
|---|---|---|---|
| HLE | 11.20375 / 563Normal (No Tools) · Text only | 6.70449 / 563Normal (No Tools) · Text only | +4.50 |
Long Context
DeepSeek-V3.1 1/1| Benchmark | DeepSeek V3.2 | DeepSeek-V3.1 | Diff |
|---|---|---|---|
| AA-LCR | 45.70144 / 170Normal (No Tools) | 47140 / 170Normal (No Tools) | -1.30 |
Math and Reasoning
DeepSeek V3.2 1/1| Benchmark | DeepSeek V3.2 | DeepSeek-V3.1 | Diff |
|---|---|---|---|
| AIME2025 | 59139 / 215Normal (No Tools) | 49.70154 / 215Normal (No Tools) | +9.30 |
Writing and Creative Capabilities
DeepSeek V3.2 1/1| Benchmark | DeepSeek V3.2 | DeepSeek-V3.1 | Diff |
|---|---|---|---|
| Creative Writing | 1,51149 / 106Normal (No Tools) | 1,43357 / 106Normal (No Tools) | +78 |
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 | Chat model |
| Architecture | MoE | MoE |
| Parameters | 671B | 671B |
| Context length | 128K | 128K |
| Max output | 8K | 8K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | DeepSeek V3.2 | DeepSeek-V3.1 |
|---|---|---|
| Text input | $0.28 / 1M tokens | $0.56 / 1M tokens |
| Text output | $0.42 / 1M tokens | $1.68 / 1M tokens |
| Cache read | $0.028 / 1M tokens | $0.28 / 1M tokens |
| Cache write | $0.28 / 1M tokens | $0.56 / 1M tokens |
Summary
- DeepSeek V3.2leads in:Coding and Software Engineer (1/1), General Evaluation (1/1), General Knowledge (1/1), Math and Reasoning (1/1), Writing and Creative Capabilities (1/1)
- DeepSeek-V3.1leads in:Long Context (1/1)
On average across the 6 shared benchmarks, DeepSeek V3.2 scores 15.60 higher.
Largest single-benchmark gap: Creative Writing — DeepSeek V3.2 1,511 vs DeepSeek-V3.1 1,433 (+78).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.