DeepSeekDeepSeek V3.2 Exp
No cheaper ranked model scores higher: it is on the price frontier.
As of 9 Nov 2026, DeepSeek V3.2 Exp by DeepSeek is not yet ranked on the BenchLeader Index, which needs at least five independent results across two categories. API pricing: $0.280 per 1M input tokens and $0.420 per 1M output tokens ($0.315 blended at 3:1), list price on 9 Nov 2026. Released 29 Sep 2025.
Key facts (as of 9 Nov 2026)
- DeepSeek V3.2 Exp API pricing: $0.280 per 1M input tokens and $0.420 per 1M output tokens ($0.315 blended at 3:1) (list price, 9 Nov 2026).
- DeepSeek V3.2 Exp was released on 29 Sep 2025 (DeepSeek).
In detail. DeepSeek V3.2 Exp is a DeepSeek open-weights model, released 29 Sep 2025. It is not yet ranked: the index needs at least five independent results across two categories. At $0.315 per million tokens blended it is cheaper than most ranked models. Last measured 29 Sep 2025.stale: no new result in six months
- Blended price
- $0.315/M
- $0.280 in · $0.420 out
- via Artificial Analysis
- Output speed
- –
- First answer
- –
- Context
- 128k
- via Artificial Analysis
- Full answer
- –
- Cost per task
- –
- Tokens per task
- –
- Released
- 29 Sep 2025
- Agents & tools56
- Instruction following45
- Long context46
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.
Reasoning
| Benchmark | no reasoning | Source |
|---|---|---|
| GPQA Diamond (AA)not in index | 73.8%#267 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 9.0%#356 | Artificial Analysis |
| CritPtnot in index | 1.4%#228 | Artificial Analysis |
Coding
| Benchmark | no reasoning | Source |
|---|---|---|
| LiveCodeBench (AA)not in index | 55.5%#123 | Artificial Analysis |
Agents & tools
| Benchmark | no reasoning | Source |
|---|---|---|
| Terminal-Bench Hard | 25.0%#141 | Artificial Analysis |
| τ²-Bench Telecom (AA)not in index | 33.9%#248 | Artificial Analysis |
Instruction following
| Benchmark | no reasoning | Source |
|---|---|---|
| IFBench | 43.1%#231 | Artificial Analysis |
Long context
| Benchmark | no reasoning | Source |
|---|---|---|
| AA-LCR v1.1 | 44.7%#361 | Artificial Analysis |
Composite
| Benchmark | no reasoning | Source |
|---|---|---|
| AA Intelligence Index v4.3.2not in index | 13.9#315 | Artificial Analysis |
| AA Progress Index v1not in index | 214.5#364 | Artificial Analysis |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0002 | – | – |
| Summarize a 30-page report | 12,000 / 600 | $0.0036 | – | – |
| Code edit | 6,000 / 1,500 | $0.0023 | – | – |
| Agentic coding session | 60,000 / 4,000 | $0.018 | – | – |
| Structured extraction | 2,000 / 200 | $0.0006 | – | – |
More from DeepSeek
See also
Questions people ask
- Why does DeepSeek V3.2 Exp have no BenchLeader Index score?
- The index needs at least five independent results across at least two categories, and as of 9 Nov 2026 DeepSeek V3.2 Exp does not have them yet. Launch-post scores are never used, so it is ranked once independent publishers have measured it.
- How much does DeepSeek V3.2 Exp cost per 1M tokens?
- As of 9 Nov 2026, DeepSeek V3.2 Exp costs $0.280 per 1M input tokens and $0.420 per 1M output tokens, $0.315 blended (three input tokens per output token).
- When was DeepSeek V3.2 Exp released?
- DeepSeek released DeepSeek V3.2 Exp on 29 Sep 2025.
Data as of 9 Nov 2026. Compare with another model.
Cite as: BenchLeader, “DeepSeek V3.2 Exp: benchmarks, pricing, speed and rank”, data as of 9 Nov 2026, https://www.benchleader.com/models/deepseek-v3-2-0925.