Qwen: Qwen3 235B A22B Thinking 2507
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pas…
qwen/qwen3-235b-a22b-thinking-2507
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144 tokens of context. This "thinking-only" variant enhances structured logical reasoning, mathematics, science, and long-form generation, showing strong benchmark performance across AIME, SuperGPQA, LiveCodeBench, and MMLU-Redux. It enforces a special reasoning mode (</think>) and is designed for high-token outputs (up to 81,920 tokens) in challenging domains.
The model is instruction-tuned and excels at step-by-step reasoning, tool use, agentic workflows, and multilingual tasks. This release represents the most capable open-source variant in the Qwen3-235B series, surpassing many closed models in structured reasoning use cases.
Specifications & capabilities
- Input
- text
- Output
- text
- Context window · tokens
- 128000
- Knowledge cutoff
- 2025-06-30
- Published model ID
- Qwen3-235B-A22B-Thinking-2507
- Capabilities
- reasoning, structuredOutputs, toolCalling
Description source ↗Evaluations
61–75 / 75
1,433.839
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Software And It Services
- dimension
- style
- metric
- Arena rating
- rank
- 169
- sample size
- 2907
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-235B-A22B-Thinking (2507)
- confidence lower
- 1422.9108202310774
- confidence upper
- 1444.7670305335791
Original result ↗1,385.414
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Instruction Following
- dimension
- style
- metric
- Arena rating
- rank
- 171
- sample size
- 2093
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-235B-A22B-Thinking (2507)
- confidence lower
- 1372.9252425170812
- confidence upper
- 1397.9032641563372
Original result ↗1,377.124
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Writing And Literature And Language
- dimension
- style
- metric
- Arena rating
- rank
- 171
- sample size
- 1859
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-235B-A22B-Thinking (2507)
- confidence lower
- 1363.4134464217218
- confidence upper
- 1390.8354762538409
Original result ↗1,442.031
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Coding
- dimension
- style
- metric
- Arena rating
- rank
- 172
- sample size
- 1590
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-235B-A22B-Thinking (2507)
- confidence lower
- 1427.3298891555978
- confidence upper
- 1456.732383458444
Original result ↗1,417.764
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Hard Prompts
- dimension
- style
- metric
- Arena rating
- rank
- 173
- sample size
- 3804
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-235B-A22B-Thinking (2507)
- confidence lower
- 1408.2837560755308
- confidence upper
- 1427.243893938737
Original result ↗1,412.81
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Life And Physical And Social Science
- dimension
- style
- metric
- Arena rating
- rank
- 173
- sample size
- 1489
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-235B-A22B-Thinking (2507)
- confidence lower
- 1397.5221630217127
- confidence upper
- 1428.0986035763383
Original result ↗1,381.605
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Spanish
- dimension
- style
- metric
- Arena rating
- rank
- 173
- sample size
- 185
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-235B-A22B-Thinking (2507)
- confidence lower
- 1341.3153397428841
- confidence upper
- 1421.8938412678935
Original result ↗1,402.288
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Longer Query
- dimension
- style
- metric
- Arena rating
- rank
- 175
- sample size
- 1637
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-235B-A22B-Thinking (2507)
- confidence lower
- 1388.0354299890046
- confidence upper
- 1416.539949655494
Original result ↗1,397.247
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Legal And Government
- dimension
- style
- metric
- Arena rating
- rank
- 177
- sample size
- 532
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-235B-A22B-Thinking (2507)
- confidence lower
- 1372.5812413070303
- confidence upper
- 1421.9119642556066
Original result ↗1,392.73
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Multi Turn
- dimension
- style
- metric
- Arena rating
- rank
- 180
- sample size
- 1355
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-235B-A22B-Thinking (2507)
- confidence lower
- 1376.976784696241
- confidence upper
- 1408.482939469413
Original result ↗1,405.559
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control English
- dimension
- style
- metric
- Arena rating
- rank
- 181
- sample size
- 3893
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-235B-A22B-Thinking (2507)
- confidence lower
- 1396.0406784768861
- confidence upper
- 1415.0765550562364
Original result ↗1,350.436
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Entertainment And Sports And Media
- dimension
- style
- metric
- Arena rating
- rank
- 183
- sample size
- 1526
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3-235B-A22B-Thinking (2507)
- confidence lower
- 1335.655773271243
- confidence upper
- 1365.2161056841871
Original result ↗22.1
- source id
- artificialAnalysis
- dimension
- coding
- metric
- Coding Index
Original result ↗12.7
- source id
- artificialAnalysis
- dimension
- intelligence
- metric
- Intelligence Index
Original result ↗1.3
- source id
- artificialAnalysis
- dimension
- agentic
- metric
- Agentic Index
Original result ↗Published prices
1–4 / 4
$0.23
- Inference provider
- deepInfra
- Platform
- DeepInfra
- Unit
- input_tokens_per_million
- Currency
- USD
$2.30
- Inference provider
- deepInfra
- Platform
- DeepInfra
- Unit
- output_tokens_per_million
- Currency
- USD
$0.45
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- input_tokens_per_million
- Currency
- USD
$3.50
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- output_tokens_per_million
- Currency
- USD
Provider specifications & access
1–8 / 8
- source model id
- HuggingFace/qwen-qwen3-235b-a22b-thinking-2507@1
- hosting
- foundry-managed-compute
- license
- apache-2.0
- source model id
- HuggingFace/qwen-qwen3-235b-a22b-thinking-2507@2
- hosting
- foundry-managed-compute
- license
- apache-2.0
- source model id
- HuggingFace/qwen-qwen3-235b-a22b-thinking-2507@3
- hosting
- foundry-managed-compute
- license
- apache-2.0
- source model id
- HuggingFace/qwen-qwen3-235b-a22b-thinking-2507@4
- hosting
- foundry-managed-compute
- license
- apache-2.0
- source model id
- HuggingFace/qwen-qwen3-235b-a22b-thinking-2507@5
- hosting
- foundry-managed-compute
- license
- apache-2.0
- source model id
- publishers/hf-qwen/models/qwen3-235b-a22b-thinking-2507@001
- hosting
- vertex-self-deployed
- source model id
- publishers/qwen/models/qwen3@qwen3-235b-a22b-thinking-2507
- hosting
- vertex-self-deployed
- source model id
- Qwen/Qwen3-235B-A22B-Thinking-2507
- hosting
- siliconflow-hosted
- max output tokens
- 262144
- capabilities
- structuredOutputs
- toolCalling
Safety assessments
1–1 / 1
26 / 100
- source id
- stanfordFMTI
- canonical model id
- qwen/qwen3-235b-a22b-thinking-2507
- 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
1–5 / 5
- field
- context_length
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 262K
- scope
- source-model
- source id
- siliconFlow
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2025-06-30
- normalized value
- 2025-06-30
- 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
- 262K
- scope
- source-model
- source id
- siliconFlow
- confidence
- 1
Explore more models