DeepSeek: DeepSeek V3.2 Exp
DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-gra…
deepseek/deepseek-v3.2-exp
DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism designed to improve training and inference efficiency in long-context scenarios while maintaining output quality. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)
The model was trained under conditions aligned with V3.1-Terminus to enable direct comparison. Benchmarking shows performance roughly on par with V3.1 across reasoning, coding, and agentic tool-use tasks, with minor tradeoffs and gains depending on the domain. This release focuses on validating architectural optimizations for extended context lengths rather than advancing raw task accuracy, making it primarily a research-oriented model for exploring efficient transformer designs.
Specifications & capabilities
- Input
- text
- Output
- text
- Context window · tokens
- 163840
- Knowledge cutoff
- 2025-07-31
- Published model ID
- DeepSeek-V3.2-Exp
- Capabilities
- reasoning, structuredOutputs, toolCalling
Description source ↗Evaluations
1–20 / 102
0.893
- source id
- llmStatsArchive
- leaderboard name
- AIME 2025 · Normalized (reported)
- dimension
- general
- metric
- AIME 2025 · Normalized (reported)
- rank
- 1
- aggregation scope
- status
- archived
- license
- CC-BY-4.0
- direction
- higherIsBetter
- conditions
- language
- en
- benchmark
- name
- AIME 2025
- language
- en
- modality
- text
- verified
- false
- max_score
- 1
- created_at
- 2025-09-05T00:00:00.000000+00:00
- paper_link
- https://arxiv.org/abs/2503.21380
- updated_at
- 2025-09-05T00:00:00.000000+00:00
- description
- All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
- benchmark_id
- aime-2025
- multilingual
- false
- analysis_method
- Pass@1 (Reasoning Mode w/o Tool Use)
- is_self_reported
- true
- verified_by_llmstats
- false
- attribution
- Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
- license_url
- https://creativecommons.org/licenses/by/4.0/
- metric_kind
- AIME 2025 · Normalized (reported)
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- data/organizations/deepseek/models/deepseek-v3.2-exp/benchmarks.json
- archive_kind
- llmStats
- evidence_url
- https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp
- git_revision
- 872b75f63b8d853c46ed17856424029a0c47b1d2
- published_at
- 2025-10-24T17:47:59Z
- snapshot_date
- 2025-10-24T17:47:59Z
- source_revision
- 6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
- publisher_anchor
- deepseek/deepseek-v3.2-exp
- metric_population
- 1
- current_catalog_url
- https://llm-stats.com/
- benchmark_evaluation
- true
- source model id
- deepseek-v3.2-exp
Original result ↗0.893
- source id
- llmStatsArchive
- leaderboard name
- AIME 2025 · Raw
- dimension
- general
- metric
- AIME 2025 · Raw
- rank
- 1
- aggregation scope
- status
- archived
- license
- CC-BY-4.0
- direction
- higherIsBetter
- conditions
- language
- en
- benchmark
- name
- AIME 2025
- language
- en
- modality
- text
- verified
- false
- max_score
- 1
- created_at
- 2025-09-05T00:00:00.000000+00:00
- paper_link
- https://arxiv.org/abs/2503.21380
- updated_at
- 2025-09-05T00:00:00.000000+00:00
- description
- All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
- benchmark_id
- aime-2025
- multilingual
- false
- analysis_method
- Pass@1 (Reasoning Mode w/o Tool Use)
- is_self_reported
- true
- verified_by_llmstats
- false
- attribution
- Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
- license_url
- https://creativecommons.org/licenses/by/4.0/
- metric_kind
- AIME 2025 · Raw
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- data/organizations/deepseek/models/deepseek-v3.2-exp/benchmarks.json
- archive_kind
- llmStats
- evidence_url
- https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp
- git_revision
- 872b75f63b8d853c46ed17856424029a0c47b1d2
- published_at
- 2025-10-24T17:47:59Z
- snapshot_date
- 2025-10-24T17:47:59Z
- source_revision
- 6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
- publisher_anchor
- deepseek/deepseek-v3.2-exp
- metric_population
- 1
- current_catalog_url
- https://llm-stats.com/
- benchmark_evaluation
- true
- source model id
- deepseek-v3.2-exp
Original result ↗0.836
- source id
- llmStatsArchive
- leaderboard name
- HMMT 2025 · Normalized (reported)
- dimension
- general
- metric
- HMMT 2025 · Normalized (reported)
- rank
- 1
- aggregation scope
- status
- archived
- license
- CC-BY-4.0
- direction
- higherIsBetter
- conditions
- language
- en
- benchmark
- name
- HMMT 2025
- language
- en
- modality
- text
- verified
- false
- max_score
- 1
- created_at
- 2025-09-05T00:00:00.000000+00:00
- paper_link
- http://web.mit.edu/HMMT/www/
- updated_at
- 2025-09-05T00:00:00.000000+00:00
- description
- Harvard-MIT Mathematics Tournament 2025 - A prestigious student-organized mathematics competition for high school students featuring two tournaments (November 2025 at MIT and February 2026 at Harvard) with individual tests, team rounds, and guts rounds
- benchmark_id
- hmmt-2025
- multilingual
- false
- analysis_method
- Pass@1 (Reasoning Mode w/o Tool Use)
- is_self_reported
- true
- verified_by_llmstats
- false
- attribution
- Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
- license_url
- https://creativecommons.org/licenses/by/4.0/
- metric_kind
- HMMT 2025 · Normalized (reported)
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- data/organizations/deepseek/models/deepseek-v3.2-exp/benchmarks.json
- archive_kind
- llmStats
- evidence_url
- https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp
- git_revision
- 872b75f63b8d853c46ed17856424029a0c47b1d2
- published_at
- 2025-10-24T17:47:59Z
- snapshot_date
- 2025-10-24T17:47:59Z
- source_revision
- 6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
- publisher_anchor
- deepseek/deepseek-v3.2-exp
- metric_population
- 1
- current_catalog_url
- https://llm-stats.com/
- benchmark_evaluation
- true
- source model id
- deepseek-v3.2-exp
Original result ↗0.836
- source id
- llmStatsArchive
- leaderboard name
- HMMT 2025 · Raw
- dimension
- general
- metric
- HMMT 2025 · Raw
- rank
- 1
- aggregation scope
- status
- archived
- license
- CC-BY-4.0
- direction
- higherIsBetter
- conditions
- language
- en
- benchmark
- name
- HMMT 2025
- language
- en
- modality
- text
- verified
- false
- max_score
- 1
- created_at
- 2025-09-05T00:00:00.000000+00:00
- paper_link
- http://web.mit.edu/HMMT/www/
- updated_at
- 2025-09-05T00:00:00.000000+00:00
- description
- Harvard-MIT Mathematics Tournament 2025 - A prestigious student-organized mathematics competition for high school students featuring two tournaments (November 2025 at MIT and February 2026 at Harvard) with individual tests, team rounds, and guts rounds
- benchmark_id
- hmmt-2025
- multilingual
- false
- analysis_method
- Pass@1 (Reasoning Mode w/o Tool Use)
- is_self_reported
- true
- verified_by_llmstats
- false
- attribution
- Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
- license_url
- https://creativecommons.org/licenses/by/4.0/
- metric_kind
- HMMT 2025 · Raw
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- data/organizations/deepseek/models/deepseek-v3.2-exp/benchmarks.json
- archive_kind
- llmStats
- evidence_url
- https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp
- git_revision
- 872b75f63b8d853c46ed17856424029a0c47b1d2
- published_at
- 2025-10-24T17:47:59Z
- snapshot_date
- 2025-10-24T17:47:59Z
- source_revision
- 6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
- publisher_anchor
- deepseek/deepseek-v3.2-exp
- metric_population
- 1
- current_catalog_url
- https://llm-stats.com/
- benchmark_evaluation
- true
- source model id
- deepseek-v3.2-exp
Original result ↗0.741
- source id
- llmStatsArchive
- leaderboard name
- LiveCodeBench · Normalized (reported)
- dimension
- general
- metric
- LiveCodeBench · Normalized (reported)
- rank
- 1
- aggregation scope
- status
- archived
- license
- CC-BY-4.0
- direction
- higherIsBetter
- conditions
- language
- en
- benchmark
- name
- LiveCodeBench
- language
- en
- modality
- text
- verified
- false
- max_score
- 1
- created_at
- 2025-07-19T19:56:13.292229+00:00
- paper_link
- https://arxiv.org/abs/2403.07974
- updated_at
- 2025-07-19T19:56:13.292229+00:00
- description
- LiveCodeBench is a holistic and contamination-free evaluation benchmark for large language models for code. It continuously collects new problems from programming contests (LeetCode, AtCoder, CodeForces) and evaluates four different scenarios: code generation, self-repair, code execution, and test output prediction. Problems are annotated with release dates to enable evaluation on unseen problems released after a model's training cutoff.
- benchmark_id
- livecodebench
- multilingual
- false
- analysis_method
- Pass@1 (Reasoning Mode w/o Tool Use)
- is_self_reported
- true
- verified_by_llmstats
- false
- attribution
- Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
- license_url
- https://creativecommons.org/licenses/by/4.0/
- metric_kind
- LiveCodeBench · Normalized (reported)
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- data/organizations/deepseek/models/deepseek-v3.2-exp/benchmarks.json
- archive_kind
- llmStats
- evidence_url
- https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp
- git_revision
- 872b75f63b8d853c46ed17856424029a0c47b1d2
- published_at
- 2025-10-24T17:47:59Z
- snapshot_date
- 2025-10-24T17:47:59Z
- source_revision
- 6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
- publisher_anchor
- deepseek/deepseek-v3.2-exp
- metric_population
- 1
- current_catalog_url
- https://llm-stats.com/
- benchmark_evaluation
- true
- source model id
- deepseek-v3.2-exp
Original result ↗0.741
- source id
- llmStatsArchive
- leaderboard name
- LiveCodeBench · Raw
- dimension
- general
- metric
- LiveCodeBench · Raw
- rank
- 1
- aggregation scope
- status
- archived
- license
- CC-BY-4.0
- direction
- higherIsBetter
- conditions
- language
- en
- benchmark
- name
- LiveCodeBench
- language
- en
- modality
- text
- verified
- false
- max_score
- 1
- created_at
- 2025-07-19T19:56:13.292229+00:00
- paper_link
- https://arxiv.org/abs/2403.07974
- updated_at
- 2025-07-19T19:56:13.292229+00:00
- description
- LiveCodeBench is a holistic and contamination-free evaluation benchmark for large language models for code. It continuously collects new problems from programming contests (LeetCode, AtCoder, CodeForces) and evaluates four different scenarios: code generation, self-repair, code execution, and test output prediction. Problems are annotated with release dates to enable evaluation on unseen problems released after a model's training cutoff.
- benchmark_id
- livecodebench
- multilingual
- false
- analysis_method
- Pass@1 (Reasoning Mode w/o Tool Use)
- is_self_reported
- true
- verified_by_llmstats
- false
- attribution
- Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
- license_url
- https://creativecommons.org/licenses/by/4.0/
- metric_kind
- LiveCodeBench · Raw
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- data/organizations/deepseek/models/deepseek-v3.2-exp/benchmarks.json
- archive_kind
- llmStats
- evidence_url
- https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp
- git_revision
- 872b75f63b8d853c46ed17856424029a0c47b1d2
- published_at
- 2025-10-24T17:47:59Z
- snapshot_date
- 2025-10-24T17:47:59Z
- source_revision
- 6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
- publisher_anchor
- deepseek/deepseek-v3.2-exp
- metric_population
- 1
- current_catalog_url
- https://llm-stats.com/
- benchmark_evaluation
- true
- source model id
- deepseek-v3.2-exp
Original result ↗93.18%
- source id
- bfcl
- leaderboard name
- BFCL Irrelevance Detection
- dimension
- toolUse
- metric
- Irrelevance detection
- rank
- 8
Original result ↗54.19%
- source id
- bfcl
- leaderboard name
- BFCL Memory
- dimension
- agentic
- metric
- Memory accuracy
- rank
- 8
Original result ↗93.75%
- source id
- bfcl
- leaderboard name
- BFCL Relevance Detection
- dimension
- toolUse
- metric
- Relevance detection
- rank
- 11
Original result ↗56.73%
- source id
- bfcl
- leaderboard name
- BFCL Overall
- dimension
- toolUse
- metric
- Overall accuracy
- rank
- 14
Original result ↗69.5%
- source id
- bfcl
- leaderboard name
- BFCL Web Search
- dimension
- agentic
- metric
- Web-search accuracy
- rank
- 16
Original result ↗44.09%
- source id
- bfcl
- leaderboard name
- BFCL Memory
- dimension
- agentic
- metric
- Memory accuracy
- rank
- 16
Original result ↗54.12%
- source id
- bfcl
- leaderboard name
- BFCL Overall
- dimension
- toolUse
- metric
- Overall accuracy
- rank
- 19
Original result ↗58%
- source id
- bfcl
- leaderboard name
- BFCL Web Search
- dimension
- agentic
- metric
- Web-search accuracy
- rank
- 22
Original result ↗44.88%
- source id
- bfcl
- leaderboard name
- BFCL Multi Turn
- dimension
- agentic
- metric
- Multi-turn accuracy
- rank
- 22
Original result ↗37.38%
- source id
- bfcl
- leaderboard name
- BFCL Multi Turn
- dimension
- agentic
- metric
- Multi-turn accuracy
- rank
- 31
Original result ↗76.02%
- source id
- bfcl
- leaderboard name
- BFCL Live
- dimension
- toolUse
- metric
- Live accuracy
- rank
- 36
Original result ↗85.52%
- source id
- bfcl
- leaderboard name
- BFCL Non-Live AST
- dimension
- toolUse
- metric
- Non-live AST accuracy
- rank
- 39
Original result ↗1,422.459
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Industry Entertainment And Sports And Media
- dimension
- factuality
- metric
- Arena rating
- rank
- 74
- sample size
- 1430
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- DeepSeek-V3.2-Exp
- confidence lower
- 1408.3011896139612
- confidence upper
- 1436.617170653869
Original result ↗1,439.818
- source id
- lmarena
- leaderboard name
- LMArena Text German
- dimension
- general
- metric
- Arena rating
- rank
- 75
- sample size
- 226
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- DeepSeek-V3.2-Exp
- confidence lower
- 1402.8757417076051
- confidence upper
- 1476.7608603123892
Original result ↗Published prices
1–6 / 6
$0.21
- Inference provider
- deepInfra
- Platform
- DeepInfra
- Unit
- input_tokens_per_million
- Currency
- USD
$0.32
- Inference provider
- deepInfra
- Platform
- DeepInfra
- Unit
- output_tokens_per_million
- Currency
- USD
$0.27
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- input_tokens_per_million
- Currency
- USD
$0.41
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- output_tokens_per_million
- Currency
- USD
$0.27
- Inference provider
- siliconFlow
- Platform
- SiliconFlow
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing label
- Input tokens (per 1M)
$0.41
- Inference provider
- siliconFlow
- Platform
- SiliconFlow
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing label
- Output tokens (per 1M)
Provider specifications & access
1–3 / 3
- source model id
- deepseek-ai/DeepSeek-V3.2-Exp
- hosting
- siliconflow-hosted
- max output tokens
- 163840
- capabilities
- reasoning
- structuredOutputs
- toolCalling
- source model id
- publishers/deepseek-ai/models/deepseek-v3-2@deepseek-v3-2-exp
- hosting
- vertex-self-deployed
- source model id
- publishers/hf-deepseek-ai/models/deepseek-v3.2-exp@001
- hosting
- vertex-self-deployed
Safety assessments
1–1 / 1
32 / 100
- source id
- stanfordFMTI
- canonical model id
- deepseek/deepseek-v3.2-exp
- taxonomy
- transparency
- hazard category
- transparency
- hazard name
- Organization transparency
- policy area
- DeepSeek
- assessment type
- organization-level disclosure
- metric
- disclosure_score
- result label
- 32 / 100
- sample size
- 100
- updated at
- 2026-11-09T18:08:05.227Z
Source specification observations
1–5 / 5
- field
- context_length
- value
- 163840
- normalized value
- 163840
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 164K
- scope
- source-model
- source id
- siliconFlow
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2025-07-31
- normalized value
- 2025-07-31
- precision
- day
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 147456
- normalized value
- 147456
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 164K
- scope
- source-model
- source id
- siliconFlow
- confidence
- 1
Explore more models