DeepSeekDeepSeek V3.2 Reasoner
DeepSeek V3.2 Reasoner is a DeepSeek open-weights model, released 1 Dec 2025. It is not yet ranked: 1 independent result so far, and the index needs at least five across two categories. Last measured 1 Dec 2025.stale: no new result in six months
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- –
- Full answer
- –
- Cost per run
- –
- Released
- 1 Dec 2025
- Coding54
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Coding
| Benchmark | not stated | Source |
|---|---|---|
| SWE-bench Verified (bash only) | 60.0%#23 | SWE-bench |
| SWE-bench Verified (any scaffold)not in index | 60.0%#30 | SWE-bench |
More from DeepSeek
See also
Questions people ask
- Why does DeepSeek V3.2 Reasoner have no BenchLeader Index score?
- The index needs at least five independent results across at least two categories; as of 25 Oct 2026 DeepSeek V3.2 Reasoner has 1 that count. Launch-post scores are never used, so it is ranked once independent publishers have measured it.
- When was DeepSeek V3.2 Reasoner released?
- DeepSeek released DeepSeek V3.2 Reasoner on 1 Dec 2025.
Data as of 25 Oct 2026. Compare with another model.
Cite as: BenchLeader, “DeepSeek V3.2 Reasoner: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/deepseek-v3-2-reasoner.