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
41–60 / 95
55.275%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · DeepInfra
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 62
- sample size
- 594
- aggregation scope
- status
- published
- harness
- url
- https://github.com/OpenRouterTeam/benchmark-harness
- name
- OpenRouter benchmark harness
- direction
- higherIsBetter
- run_count
- 3
- conditions
- window
- newest 90 days; successful visible nonzero runs
- dataset
- benchmark-leaderboard
- benchmark
- id
- gpqa_diamond
- name
- GPQA Diamond
- 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
- 2026-10-08T23:30:03.872Z
- 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
- 594
- source_file
- benchmark-leaderboard.json
- source_page
- https://openrouter.ai/benchmarks/gpqa-diamond
- measurements
- accuracy
- 0.5527496666666667
- accuracy_std_dev
- 0.01040809115811132
- cost_per_task_usd
- 0.004829589225589226
- output_tokens_per_task
- 17015.548821548822
- latency_seconds_per_task
- 647.9304865319865
- 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
- 71
- benchmark_evaluation
- true
- openrouter_permaslug
- qwen/qwen3-32b-04-28
- source model id
- qwen/qwen3-32b-04-28
Original result ↗76.37%
- source id
- bfcl
- leaderboard name
- BFCL Irrelevance Detection
- dimension
- toolUse
- metric
- Irrelevance detection
- rank
- 68
Original result ↗47%
- source id
- openRouterBenchmarks
- leaderboard name
- tau2-bench Verified Airline · Accuracy · auto-routing
- dimension
- agentic
- metric
- tau2-bench Verified Airline · Accuracy
- rank
- 108
- 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
- auto-routing
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-08-29T16:16:50.456Z
- 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
- 0.47
- accuracy_std_dev
- 0.009999999999999981
- cost_per_task_usd
- 0.02032128
- output_tokens_per_task
- 18360.23
- latency_seconds_per_task
- 826.13539
- 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
- 128
- benchmark_evaluation
- true
- openrouter_permaslug
- qwen/qwen3-32b-04-28
- source model id
- qwen/qwen3-32b-04-28
Original result ↗60.943%
- source id
- openRouterBenchmarks
- leaderboard name
- GPQA Diamond · Accuracy · auto-routing
- dimension
- knowledge
- metric
- GPQA Diamond · Accuracy
- rank
- 116
- 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
- auto-routing
- attribution
- Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
- last_run_at
- 2026-08-29T19:52:22.642Z
- 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
- 0.6094280000000001
- accuracy_std_dev
- 0.010100999999999971
- cost_per_task_usd
- 0.008297136363636364
- output_tokens_per_task
- 17281.333333333332
- latency_seconds_per_task
- 338.1577095959596
- 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
- 132
- benchmark_evaluation
- true
- openrouter_permaslug
- qwen/qwen3-32b-04-28
- source model id
- qwen/qwen3-32b-04-28
Original result ↗1,424.8
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Mathematical
- dimension
- style
- metric
- Arena rating
- rank
- 135
- sample size
- 282
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-32B
- confidence lower
- 1392.7475667250396
- confidence upper
- 1456.8517030125415
Original result ↗1,419.891
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Mathematical
- dimension
- general
- metric
- Arena rating
- rank
- 136
- sample size
- 282
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-32B
- confidence lower
- 1388.3219300431429
- confidence upper
- 1451.4597934522426
Original result ↗1,398.545
- source id
- lmarena
- leaderboard name
- LMArena Text Math
- dimension
- general
- metric
- Arena rating
- rank
- 161
- sample size
- 316
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-32B
- confidence lower
- 1368.5866264573622
- confidence upper
- 1428.5028445560097
Original result ↗1,398.071
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Math
- dimension
- style
- metric
- Arena rating
- rank
- 166
- sample size
- 316
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-32B
- confidence lower
- 1368.0131386069238
- confidence upper
- 1428.1289423771127
Original result ↗1,341.08
- source id
- lmarena
- leaderboard name
- LMArena Text German
- dimension
- general
- metric
- Arena rating
- rank
- 184
- sample size
- 172
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-32B
- confidence lower
- 1300.3950550517227
- confidence upper
- 1381.7647941413502
Original result ↗1,397.497
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Expert
- dimension
- style
- metric
- Arena rating
- rank
- 189
- sample size
- 236
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-32B
- confidence lower
- 1360.1684170618796
- confidence upper
- 1434.8258555216148
Original result ↗1,368.331
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Medicine And Healthcare
- dimension
- general
- metric
- Arena rating
- rank
- 191
- sample size
- 212
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-32B
- confidence lower
- 1329.9365508412234
- confidence upper
- 1406.7254597247957
Original result ↗1,361.842
- source id
- lmarena
- leaderboard name
- LMArena Text Expert
- dimension
- general
- metric
- Arena rating
- rank
- 192
- sample size
- 236
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-32B
- confidence lower
- 1325.4613006866284
- confidence upper
- 1398.2233636224064
Original result ↗1,334.817
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control German
- dimension
- style
- metric
- Arena rating
- rank
- 192
- sample size
- 172
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-32B
- confidence lower
- 1293.5735232644474
- confidence upper
- 1376.059839679965
Original result ↗1,372.168
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Life And Physical And Social Science
- dimension
- general
- metric
- Arena rating
- rank
- 199
- sample size
- 798
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-32B
- confidence lower
- 1351.9286792472544
- confidence upper
- 1392.4063787373116
Original result ↗1,379.177
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Medicine And Healthcare
- dimension
- style
- metric
- Arena rating
- rank
- 210
- sample size
- 212
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-32B
- confidence lower
- 1340.2858767929388
- confidence upper
- 1418.068317986812
Original result ↗1,378.684
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Life And Physical And Social Science
- dimension
- style
- metric
- Arena rating
- rank
- 211
- sample size
- 798
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-32B
- confidence lower
- 1358.2830740546085
- confidence upper
- 1399.0843358048116
Original result ↗1,406.004
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Coding
- dimension
- style
- metric
- Arena rating
- rank
- 212
- sample size
- 513
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-32B
- confidence lower
- 1381.7614954213493
- confidence upper
- 1430.2471237114378
Original result ↗1,397.505
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Software And It Services
- dimension
- style
- metric
- Arena rating
- rank
- 213
- sample size
- 843
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-32B
- confidence lower
- 1378.2676547892456
- confidence upper
- 1416.7432891233243
Original result ↗1,365.907
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Software And It Services
- dimension
- general
- metric
- Arena rating
- rank
- 214
- sample size
- 843
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-32B
- confidence lower
- 1346.9004400798333
- confidence upper
- 1384.9141061781274
Original result ↗1,357
- source id
- lmarena
- leaderboard name
- LMArena Text Chinese
- dimension
- general
- metric
- Arena rating
- rank
- 214
- sample size
- 187
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-32B
- confidence lower
- 1319.850386566399
- confidence upper
- 1394.1494385499877
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