DeepSeek V3.2 Reasoner: benchmark scores, price and ranking
DeepSeek V3.2 Reasoner from deepseek ranks #202 of 743 LLMs on the LLMs Tiger aggregate benchmark score (50.3), based on 1 benchmark results captured up to 2026-10-13.
- Organisation
- deepseek
- Type
- Open-weight / local model
- Open weights
- Yes
- Aggregate rank
- #202 of 743 (score 50.3)
Across the 1 benchmark where at least ten models are scored, DeepSeek V3.2 Reasoner is in the top 10% on 0 and in the top half on 1.
DeepSeek V3.2 Reasoner benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| SWE-bench Verified | 60.0% | #34 of 73 | SWE-bench Verified leaderboard | 2026-10-13 |
About DeepSeek V3.2 Reasoner
DeepSeek V3.2 Reasoner is an open-weight model that can run on your own hardware from deepseek. No API price is listed for it yet. We hold 1 benchmark result for it across 1 area, and none is in the top tenth of its board.
Where DeepSeek V3.2 Reasoner stands
On our aggregate score, DeepSeek V3.2 Reasoner is #202 of 743 ranked models, around the middle of the table. Its score is 50.3; the scale is centred on 50, so it sits 0.3 points above the typical model. That beats 73% of the ranked field.
DeepSeek V3.2 Reasoner, benchmark by benchmark
SWE-bench Verified puts DeepSeek V3.2 Reasoner at 60.0%, #34 of 73. That beats 53% of the models tested, but 23.5 points short of Claude Opus 4.7 (max) (83.5%). The results either side are Qwen3-Coder-30B-A3B-Instruct (60.4%) and TTS(Bo16) (58.8%). It covers real GitHub issues resolved. The board median is 56.4%, so DeepSeek V3.2 Reasoner is 3.6 points above it. Source: SWE-bench Verified leaderboard, captured 2026-10-13.
Reading these numbers
The 1 score on this page comes from 1 source: SWE-bench Verified leaderboard (1). 1 of them come from an official leaderboard and 0 from datasets or third-party runs. With 1 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #199 Grok Build + Grok 4.7 (50.3)
- #200 CodeAct v1.8 (50.3)
- #201 Codex + GPT-5.6 Sol (50.3)
- #203 chatgpt-4o-latest (2025-03-29) (50.2)
- #204 GPT-5.1-Codex-Max (50.2)
- #205 gpt-4.5-preview (50.2)
Compare it on the live leaderboard → · How the aggregate score works