DeepSeek V3.2vsDeepSeek-V3-0324
Across 8 shared benchmarks, DeepSeek V3.2 leads overall: DeepSeek V3.2 wins 8, DeepSeek-V3-0324 wins 0, with 0 ties and an average score difference of +31.50.
DeepSeek V3.2
DeepSeek-AI · 2025-12-01 · Reasoning model
DeepSeek-V3-0324
DeepSeek-AI · 2025-03-24 · Chat model
DeepSeek V3.28 wins(100%)(0%)0 winsDeepSeek-V3-0324
Benchmark scores
Grouped by capability, sorted by largest gap within each. 8 shared benchmarks.
General Knowledge
DeepSeek V3.2 3/3| Benchmark | DeepSeek V3.2 | DeepSeek-V3-0324 | Diff |
|---|---|---|---|
| ARC-AGI | 5738 / 65Thinking (No Tools) | 959 / 65 | +48 |
| HLE | 25.1087 / 157Thinking (No Tools) | 5.20150 / 157 | +19.90 |
| GPQA Diamond | 82.4064 / 178Thinking (No Tools) | 68.40119 / 178 | +14 |
Agent Level Benchmark
DeepSeek V3.2 2/2| Benchmark | DeepSeek V3.2 | DeepSeek-V3-0324 | Diff |
|---|---|---|---|
| τ²-Bench | 80.3014 / 40 | 38.8036 / 40 | +41.50 |
| Aider-Polyglot | 69.9012 / 26 | 55.1021 / 26 | +14.80 |
Coding and Software Engineer
DeepSeek V3.2 2/2| Benchmark | DeepSeek V3.2 | DeepSeek-V3-0324 | Diff |
|---|---|---|---|
| SWE-bench Verified | 73.1045 / 108 | 38.8099 / 108 | +34.30 |
| LiveCodeBench | 83.3021 / 120Thinking (No Tools) | 49.2093 / 120 | +34.10 |
Math and Reasoning
DeepSeek V3.2 1/1| Benchmark | DeepSeek V3.2 | DeepSeek-V3-0324 | Diff |
|---|---|---|---|
| AIME2025 | 93.1030 / 106Thinking (No Tools) | 47.7088 / 106 | +45.40 |
Specs
| Field | DeepSeek V3.2 | DeepSeek-V3-0324 |
|---|---|---|
| Publisher | DeepSeek-AI | DeepSeek-AI |
| Release date | 2025-12-01 | 2025-03-24 |
| Model type | Reasoning model | Chat model |
| Architecture | MoE | MoE |
| Parameters | 671B | 671B |
| Context length | 128K | 128K |
| Max output | 8K | Not available |
Summary
- DeepSeek V3.2leads in:General Knowledge (3/3), Agent Level Benchmark (2/2), Coding and Software Engineer (2/2), Math and Reasoning (1/1)
On average across the 8 shared benchmarks, DeepSeek V3.2 scores 31.50 higher.
Largest single-benchmark gap: ARC-AGI — DeepSeek V3.2 57 vs DeepSeek-V3-0324 9 (+48).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.