Qwen: Qwen3 32B
Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode…
qwen/qwen3-32b-04-28
Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for tasks like math, coding, and logical inference, and a "non-thinking" mode for faster, general-purpose conversation. The model demonstrates strong performance in instruction-following, agent tool use, creative writing, and multilingual tasks across 100+ languages and dialects. It natively handles 32K token contexts and can extend to 131K tokens using YaRN-based scaling.
Specifications & capabilities
- Input
- text
- Output
- text
- Context window · tokens
- 131072
- Knowledge cutoff
- 2025-03-31
- Published model ID
- Qwen3-32B
- Capabilities
- reasoning, structuredOutputs, toolCalling
Description source ↗Evaluations
21–40 / 95
47.667%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · Nebius
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 19
- sample size
- 100
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 2
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- tau_bench_verified_airline
- name
- tau2-bench Verified Airline
- record_kind
- aggregate
- provider_name
- Nebius
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-08-29T16:13:54.382Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- tau2-bench Verified Airline · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 100
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.476667
- accuracy_std_dev
- 0.010000000000000009
- cost_per_task_usd
- 0.023033520000000002
- output_tokens_per_task
- 22315.68
- latency_seconds_per_task
- 894.80372
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 23
- benchmark_evaluation
- true
- openrouter_permaslug
- qwen/qwen3-32b-04-28
- source model id
- qwen/qwen3-32b-04-28
Original result ↗61.364%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · Nebius
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 23
- sample size
- 396
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 2
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- record_kind
- aggregate
- provider_name
- Nebius
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-08-29T19:06:01.882Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- GPQA Diamond · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 396
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.6136364999999999
- accuracy_std_dev
- 0.007575500000000013
- cost_per_task_usd
- 0.005658078282828283
- output_tokens_per_task
- 18940.444444444445
- latency_seconds_per_task
- 686.3842954545454
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 25
- benchmark_evaluation
- true
- openrouter_permaslug
- qwen/qwen3-32b-04-28
- source model id
- qwen/qwen3-32b-04-28
Original result ↗93.75%
- source id
- bfcl
- leaderboard name
- BFCL Relevance Detection
- dimension
- toolUse
- metric
- Relevance detection
- rank
- 25
Original result ↗43.25%
- source id
- bfcl
- leaderboard name
- BFCL Multi Turn
- dimension
- agentic
- metric
- Multi-turn accuracy
- rank
- 25
Original result ↗26.67%
- source id
- bfcl
- leaderboard name
- BFCL Memory
- dimension
- agentic
- metric
- Memory accuracy
- rank
- 28
Original result ↗48.71%
- source id
- bfcl
- leaderboard name
- BFCL Overall
- dimension
- toolUse
- metric
- Overall accuracy
- rank
- 29
Original result ↗57.6%
- source id
- openCompass
- leaderboard name
- LiveCodeBenchV6
- dimension
- general
- metric
- LiveCodeBenchV6
- rank
- 31
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- OverallTable
- catalog
- open
- snapshot
- month
- REALTIME
- fileName
- assets/research-rank/research-data.REALTIME.20260309.json
- updateTime
- 2026-03-09
- columnFileName
- assets/research-rank/research-column.REALTIME.20260309.json
- metric_kind
- LiveCodeBenchV6
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 0-data.json
- source_revision
- 117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
- metric_population
- 48
- benchmark_evaluation
- true
- source model id
- Qwen3-32B (Thinking)
Original result ↗70.3%
- source id
- openCompass
- leaderboard name
- AIME2025
- dimension
- general
- metric
- AIME2025
- rank
- 33
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- OverallTable
- catalog
- open
- snapshot
- month
- REALTIME
- fileName
- assets/research-rank/research-data.REALTIME.20260309.json
- updateTime
- 2026-03-09
- columnFileName
- assets/research-rank/research-column.REALTIME.20260309.json
- metric_kind
- AIME2025
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 0-data.json
- source_revision
- 117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
- metric_population
- 48
- benchmark_evaluation
- true
- source model id
- Qwen3-32B (Thinking)
Original result ↗46.78%
- source id
- bfcl
- leaderboard name
- BFCL Overall
- dimension
- toolUse
- metric
- Overall accuracy
- rank
- 33
Original result ↗61.3%
- source id
- openCompass
- leaderboard name
- Average
- dimension
- general
- metric
- Average
- rank
- 34
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- OverallTable
- catalog
- open
- snapshot
- month
- REALTIME
- fileName
- assets/research-rank/research-data.REALTIME.20260309.json
- updateTime
- 2026-03-09
- columnFileName
- assets/research-rank/research-column.REALTIME.20260309.json
- metric_kind
- Average
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 0-data.json
- source_revision
- 117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
- metric_population
- 48
- benchmark_evaluation
- true
- source model id
- Qwen3-32B (Thinking)
Original result ↗8.5%
- source id
- openCompass
- leaderboard name
- HLE
- dimension
- general
- metric
- HLE
- rank
- 34
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- OverallTable
- catalog
- open
- snapshot
- month
- REALTIME
- fileName
- assets/research-rank/research-data.REALTIME.20260309.json
- updateTime
- 2026-03-09
- columnFileName
- assets/research-rank/research-column.REALTIME.20260309.json
- metric_kind
- HLE
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 0-data.json
- source_revision
- 117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
- metric_population
- 48
- benchmark_evaluation
- true
- source model id
- Qwen3-32B (Thinking)
Original result ↗86%
- source id
- openCompass
- leaderboard name
- IFEval
- dimension
- general
- metric
- IFEval
- rank
- 37
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- OverallTable
- catalog
- open
- snapshot
- month
- REALTIME
- fileName
- assets/research-rank/research-data.REALTIME.20260309.json
- updateTime
- 2026-03-09
- columnFileName
- assets/research-rank/research-column.REALTIME.20260309.json
- metric_kind
- IFEval
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 0-data.json
- source_revision
- 117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
- metric_population
- 48
- benchmark_evaluation
- true
- source model id
- Qwen3-32B (Thinking)
Original result ↗78%
- source id
- openCompass
- leaderboard name
- MMLU-Pro
- dimension
- general
- metric
- MMLU-Pro
- rank
- 37
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- OverallTable
- catalog
- open
- snapshot
- month
- REALTIME
- fileName
- assets/research-rank/research-data.REALTIME.20260309.json
- updateTime
- 2026-03-09
- columnFileName
- assets/research-rank/research-column.REALTIME.20260309.json
- metric_kind
- MMLU-Pro
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 0-data.json
- source_revision
- 117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
- metric_population
- 48
- benchmark_evaluation
- true
- source model id
- Qwen3-32B (Thinking)
Original result ↗26%
- source id
- bfcl
- leaderboard name
- BFCL Web Search
- dimension
- agentic
- metric
- Web-search accuracy
- rank
- 38
Original result ↗67.3%
- source id
- openCompass
- leaderboard name
- GPQA-Diamond
- dimension
- general
- metric
- GPQA-Diamond
- rank
- 40
- aggregation scope
- status
- published
- direction
- higherIsBetter
- conditions
- suite
- OverallTable
- catalog
- open
- snapshot
- month
- REALTIME
- fileName
- assets/research-rank/research-data.REALTIME.20260309.json
- updateTime
- 2026-03-09
- columnFileName
- assets/research-rank/research-column.REALTIME.20260309.json
- metric_kind
- GPQA-Diamond
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 0-data.json
- source_revision
- 117c5effa3066abf39f3e8f61109707b09f0cd95223246c07acd6289f4f7fcd2
- metric_population
- 48
- benchmark_evaluation
- true
- source model id
- Qwen3-32B (Thinking)
Original result ↗21.5%
- source id
- bfcl
- leaderboard name
- BFCL Web Search
- dimension
- agentic
- metric
- Web-search accuracy
- rank
- 42
Original result ↗82.39%
- source id
- bfcl
- leaderboard name
- BFCL Irrelevance Detection
- dimension
- toolUse
- metric
- Irrelevance detection
- rank
- 45
Original result ↗47.167%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · DeepInfra
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 51
- sample size
- 100
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 2
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- tau_bench_verified_airline
- name
- tau2-bench Verified Airline
- record_kind
- aggregate
- provider_name
- DeepInfra
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-10-09T00:21:42.483Z
- license_url
- https://creativecommons.org/licenses/by/4.0/
- methodology
- Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
- metric_kind
- tau2-bench Verified Airline · Accuracy
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- sample_size
- 100
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/tau2-bench-airline
- measurements
- accuracy
- 0.47166650000000004
- accuracy_std_dev
- 0.011666499999999996
- cost_per_task_usd
- 0.02012662
- output_tokens_per_task
- 18771.04
- latency_seconds_per_task
- 866.8746
- published_at
- 2026-11-16T01:46:02.653Z
- snapshot_date
- 2026-11-16
- source_revision
- 7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
- transformations
- TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
- metric_population
- 63
- benchmark_evaluation
- true
- openrouter_permaslug
- qwen/qwen3-32b-04-28
- source model id
- qwen/qwen3-32b-04-28
Original result ↗15.7%
- source id
- bfcl
- leaderboard name
- BFCL Memory
- dimension
- agentic
- metric
- Memory accuracy
- rank
- 55
Original result ↗81.25%
- source id
- bfcl
- leaderboard name
- BFCL Relevance Detection
- dimension
- toolUse
- metric
- Relevance detection
- rank
- 59
Original result ↗Published prices
1–4 / 4
$0.08
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- input_tokens_per_million
- Currency
- USD
$0.28
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- output_tokens_per_million
- Currency
- USD
$0.14
- Inference provider
- siliconFlow
- Platform
- SiliconFlow
- Unit
- input_tokens_per_million
- Currency
- USD
- Billing label
- Input tokens (per 1M)
$0.57
- Inference provider
- siliconFlow
- Platform
- SiliconFlow
- Unit
- output_tokens_per_million
- Currency
- USD
- Billing label
- Output tokens (per 1M)
Provider specifications & access
1–9 / 9
- source model id
- azure-huggingface/qwen--qwen3-32b@2
- hosting
- foundry-managed-compute
- license
- apache-2.0
- context length
- 40960
- source model id
- azure-huggingface/qwen--qwen3-32b@3
- hosting
- foundry-managed-compute
- license
- apache-2.0
- context length
- 40960
- source model id
- azure-huggingface/qwen--qwen3-32b@4
- hosting
- foundry-managed-compute
- license
- apache-2.0
- context length
- 40960
- source model id
- azure-huggingface/qwen--qwen3-32b@5
- hosting
- foundry-managed-compute
- license
- apache-2.0
- context length
- 40960
- source model id
- azure-huggingface/qwen--qwen3-32b@6
- hosting
- foundry-managed-compute
- license
- apache-2.0
- context length
- 40960
- source model id
- HuggingFace/qwen-qwen3-32b@1
- hosting
- foundry-managed-compute
- license
- apache-2.0
- source model id
- HuggingFace/qwen-qwen3-32b@2
- hosting
- foundry-managed-compute
- license
- apache-2.0
- source model id
- publishers/qwen/models/qwen3@qwen3-32b
- hosting
- vertex-self-deployed
- source model id
- Qwen/Qwen3-32B
- hosting
- siliconflow-hosted
- max output tokens
- 131072
- capabilities
- reasoning
- structuredOutputs
- toolCalling
Safety assessments
1–1 / 1
26 / 100
- source id
- stanfordFMTI
- canonical model id
- qwen/qwen3-32b-04-28
- taxonomy
- transparency
- hazard category
- transparency
- hazard name
- Organization transparency
- policy area
- Alibaba
- assessment type
- organization-level disclosure
- metric
- disclosure_score
- result label
- 26 / 100
- sample size
- 100
- updated at
- 2026-11-09T18:08:05.227Z
Source specification observations
1–10 / 10
- field
- context_length
- value
- 40960
- normalized value
- 40960
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- context_length
- value
- 40960
- normalized value
- 40960
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- context_length
- value
- 40960
- normalized value
- 40960
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- context_length
- value
- 40960
- normalized value
- 40960
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- context_length
- value
- 40960
- normalized value
- 40960
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- context_length
- value
- 131072
- normalized value
- 131072
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 131K
- scope
- source-model
- source id
- siliconFlow
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2025-03-31
- normalized value
- 2025-03-31
- precision
- day
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 16384
- normalized value
- 16384
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 131K
- scope
- source-model
- source id
- siliconFlow
- confidence
- 1
Hugging Face model card
1–1 / 1
- downloads
- 3062101
- likes
- 792
- pipeline tag
- text-generation
- library name
- transformers
- License
- apache-2.0
Explore more models