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

21–40 / 75

LMArena

1,386.733

source id
lmarena
leaderboard name
LMArena Text Japanese
dimension
general
metric
Arena rating
rank
98
sample size
442
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-235B-A22B-Thinking (2507)
confidence lower
1357.3126690832294
confidence upper
1416.1542860652064
Original result ↗

LMArena

1,435.446

source id
lmarena
leaderboard name
LMArena Text Industry Mathematical
dimension
general
metric
Arena rating
rank
107
sample size
475
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-235B-A22B-Thinking (2507)
confidence lower
1409.7186035963032
confidence upper
1461.1729985993584
Original result ↗

LMArena

1,374.828

source id
lmarena
leaderboard name
LMArena Text Korean
dimension
general
metric
Arena rating
rank
107
sample size
204
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-235B-A22B-Thinking (2507)
confidence lower
1333.8668779751983
confidence upper
1415.7885073381806
Original result ↗

LMArena

1,376.262

source id
lmarena
leaderboard name
LMArena Text Style Control Japanese
dimension
style
metric
Arena rating
rank
115
sample size
442
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-235B-A22B-Thinking (2507)
confidence lower
1346.6309620372801
confidence upper
1405.8935630330975
Original result ↗

LMArena

1,408.078

source id
lmarena
leaderboard name
LMArena Text German
dimension
general
metric
Arena rating
rank
119
sample size
211
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-235B-A22B-Thinking (2507)
confidence lower
1368.432551717833
confidence upper
1447.7238340373895
Original result ↗

LMArena

1,433.787

source id
lmarena
leaderboard name
LMArena Text Industry Life And Physical And Social Science
dimension
general
metric
Arena rating
rank
120
sample size
1489
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-235B-A22B-Thinking (2507)
confidence lower
1418.5366651355016
confidence upper
1449.0369191993536
Original result ↗

LMArena

1,430.07

source id
lmarena
leaderboard name
LMArena Text English
dimension
general
metric
Arena rating
rank
120
sample size
3893
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-235B-A22B-Thinking (2507)
confidence lower
1420.644067189715
confidence upper
1439.4954954254258
Original result ↗

LMArena

1,412.445

source id
lmarena
leaderboard name
LMArena Text Industry Business And Management And Financial Operations
dimension
general
metric
Arena rating
rank
122
sample size
1525
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-235B-A22B-Thinking (2507)
confidence lower
1397.4110974620282
confidence upper
1427.4795380593443
Original result ↗

LMArena

1,431.996

source id
lmarena
leaderboard name
LMArena Text Hard Prompts English
dimension
general
metric
Arena rating
rank
125
sample size
1715
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-235B-A22B-Thinking (2507)
confidence lower
1417.935153539016
confidence upper
1446.056596547346
Original result ↗

LMArena

1,383.833

source id
lmarena
leaderboard name
LMArena Text Creative Writing
dimension
general
metric
Arena rating
rank
129
sample size
1083
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-235B-A22B-Thinking (2507)
confidence lower
1366.1461810497642
confidence upper
1401.5194807602786
Original result ↗

LMArena

1,440.636

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Medicine And Healthcare
dimension
style
metric
Arena rating
rank
130
sample size
507
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-235B-A22B-Thinking (2507)
confidence lower
1414.2713328745153
confidence upper
1467.0000408905491
Original result ↗

LMArena

1,362.197

source id
lmarena
leaderboard name
LMArena Text Style Control Korean
dimension
style
metric
Arena rating
rank
130
sample size
204
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-235B-A22B-Thinking (2507)
confidence lower
1321.0265580749538
confidence upper
1403.3672067516563
Original result ↗

LMArena

1,402.138

source id
lmarena
leaderboard name
LMArena Text Exclude Ties
dimension
general
metric
Arena rating
rank
132
sample size
6201
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-235B-A22B-Thinking (2507)
confidence lower
1392.8102474398684
confidence upper
1411.4659045728476
Original result ↗

LMArena

1,415.543

source id
lmarena
leaderboard name
LMArena Text Overall
dimension
general
metric
Arena rating
rank
133
sample size
8812
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-235B-A22B-Thinking (2507)
confidence lower
1409.0052487947692
confidence upper
1422.0806693876561
Original result ↗

LMArena

1,400.853

source id
lmarena
leaderboard name
LMArena Text Style Control German
dimension
style
metric
Arena rating
rank
134
sample size
211
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-235B-A22B-Thinking (2507)
confidence lower
1360.8107607877082
confidence upper
1440.8956074663242
Original result ↗

LMArena

1,400.342

source id
lmarena
leaderboard name
LMArena Text Russian
dimension
general
metric
Arena rating
rank
134
sample size
527
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-235B-A22B-Thinking (2507)
confidence lower
1376.4700463586175
confidence upper
1424.2131699163067
Original result ↗

LMArena

1,454.283

source id
lmarena
leaderboard name
LMArena Text Style Control Chinese
dimension
style
metric
Arena rating
rank
135
sample size
535
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-235B-A22B-Thinking (2507)
confidence lower
1428.4924656259661
confidence upper
1480.0735824259573
Original result ↗

LMArena

1,387.771

source id
lmarena
leaderboard name
LMArena Text Industry Writing And Literature And Language
dimension
general
metric
Arena rating
rank
136
sample size
1859
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-235B-A22B-Thinking (2507)
confidence lower
1374.2853011889342
confidence upper
1401.2574822320958
Original result ↗

LMArena

1,421.696

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Mathematical
dimension
style
metric
Arena rating
rank
138
sample size
475
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-235B-A22B-Thinking (2507)
confidence lower
1396.080043773727
confidence upper
1447.312011063783
Original result ↗

LMArena

1,389.358

source id
lmarena
leaderboard name
LMArena Text Polish
dimension
general
metric
Arena rating
rank
138
sample size
784
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-235B-A22B-Thinking (2507)
confidence lower
1368.7291271099189
confidence upper
1409.9861906615856
Original result ↗

Published prices

1–4 / 4

Provider specifications & access

1–8 / 8

Qwen/Qwen3-235B-A22B-Thinking-2507 ↗

source model id
HuggingFace/qwen-qwen3-235b-a22b-thinking-2507@1
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
apache-2.0
architecture
input_modalities
  • text
output_modalities
  • text
capabilities

    Qwen/Qwen3-235B-A22B-Thinking-2507 ↗

    source model id
    HuggingFace/qwen-qwen3-235b-a22b-thinking-2507@2
    hosting
    foundry-managed-compute
    platforms
    • Microsoft Foundry
    license
    apache-2.0
    architecture
    input_modalities
    • text
    output_modalities
    • text
    capabilities

      Qwen/Qwen3-235B-A22B-Thinking-2507 ↗

      source model id
      HuggingFace/qwen-qwen3-235b-a22b-thinking-2507@3
      hosting
      foundry-managed-compute
      platforms
      • Microsoft Foundry
      license
      apache-2.0
      architecture
      input_modalities
      • text
      output_modalities
      • text
      capabilities

        Qwen/Qwen3-235B-A22B-Thinking-2507 ↗

        source model id
        HuggingFace/qwen-qwen3-235b-a22b-thinking-2507@4
        hosting
        foundry-managed-compute
        platforms
        • Microsoft Foundry
        license
        apache-2.0
        architecture
        input_modalities
        • text
        output_modalities
        • text
        capabilities

          Qwen/Qwen3-235B-A22B-Thinking-2507 ↗

          source model id
          HuggingFace/qwen-qwen3-235b-a22b-thinking-2507@5
          hosting
          foundry-managed-compute
          platforms
          • Microsoft Foundry
          license
          apache-2.0
          architecture
          input_modalities
          • text
          output_modalities
          • text
          capabilities

            Qwen/Qwen3-235B-A22B-Thinking-2507 ↗

            source model id
            publishers/hf-qwen/models/qwen3-235b-a22b-thinking-2507@001
            hosting
            vertex-self-deployed
            platforms
            • Google Cloud Vertex AI
            architecture
            input_modalities
            • text
            output_modalities
            • text
            capabilities

              Qwen3-235B-A22B-Thinking-2507 ↗

              source model id
              publishers/qwen/models/qwen3@qwen3-235b-a22b-thinking-2507
              hosting
              vertex-self-deployed
              platforms
              • Google Cloud Vertex AI
              architecture
              input_modalities
              • text
              output_modalities
              • text
              capabilities

                Qwen3-235B-A22B-Thinking-2507 ↗

                source model id
                Qwen/Qwen3-235B-A22B-Thinking-2507
                hosting
                siliconflow-hosted
                platforms
                • SiliconFlow
                max output tokens
                262144
                architecture
                input_modalities
                • text
                output_modalities
                • text
                capabilities
                • structuredOutputs
                • toolCalling

                Safety assessments

                1–1 / 1

                Foundation Model Transparency Index 2025 ↗

                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

                openRouter ↗

                field
                context_length
                value
                128000
                normalized value
                128000
                scope
                source-model
                source id
                openRouter
                confidence
                1

                siliconFlow ↗

                field
                context_length
                value
                262K
                scope
                source-model
                source id
                siliconFlow
                confidence
                1

                openRouter ↗

                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

                openRouter ↗

                field
                max_output_tokens
                value
                16384
                normalized value
                16384
                scope
                source-model
                source id
                openRouter
                confidence
                1

                siliconFlow ↗

                field
                max_output_tokens
                value
                262K
                scope
                source-model
                source id
                siliconFlow
                confidence
                1

                Original sources

                1–20 / 25

                SiliconFlow · Model page ↗

                Hugging Face · Model repository ↗

                DeepInfra · Model page ↗

                Google Cloud · Model page ↗

                Google Cloud · Model page ↗

                Microsoft Foundry · Model page ↗

                Microsoft Foundry · Model page ↗

                Microsoft Foundry · Model page ↗

                Microsoft Foundry · Model page ↗

                Microsoft Foundry · Model page ↗

                OpenRouter · Model page ↗

                SiliconFlow · Playground ↗

                Google Cloud · Model documentation ↗

                Microsoft Foundry · Model documentation ↗

                SiliconFlow · API documentation ↗

                DeepInfra · Catalog ↗

                GitHub · Catalog ↗

                GitHub · Catalog ↗

                Google Cloud · Catalog ↗

                Hugging Face · Catalog ↗

                Source links

                1–12 / 12

                Explore more models

                Models

                Loading
                EVIDENCE / COMPARISON

                Benchmarks

                Explore every benchmark

                Loading

                These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

                Install TensorTrace