Qwen/QwQ-32B-Preview

Preview QwQ 32B reasoning model for experimental math and coding tasks.

azureFoundry/azure-huggingface/qwen--qwq-32b-preview@5

Preview QwQ 32B reasoning model for experimental math and coding tasks.

Specifications & capabilities

Input
text
Output
text
Context window · tokens
32768
Published model ID
QwQ-32B-Preview

Evaluations

21–40 / 75

Open LLM Leaderboard v2

66.914%

source id
openLLMLeaderboardV2
leaderboard name
Open LLM v2 BBH · Raw
dimension
reasoning
metric
Raw accuracy
rank
220
aggregation scope
suite
Open LLM v2
co2_kg
20.42077955247921
status
archived
precision
bfloat16
task_count
6
metric_kind
Raw accuracy
rank_method
Derived competition rank over published evaluations with reported scores, including variants and source flags
weight_type
Original
published_at
2025-03-20T12:17:27Z
chat_template
true
suite_version
2
model_revision
1032e81cb936c486aae1d33da75b2fbcd5deed4a
source_flagged
false
missing_metrics
    dataset_revision
    9c09a7cae43334062a82cb164f2ef255013dafa2
    metric_population
    4576
    ranking_population
    4576
    source_flag_anomaly
    false
    source model id
    Qwen/QwQ-32B-Preview
    Original result ↗

    LMArena

    1,221.542

    source id
    lmarena
    leaderboard name
    LMArena Text Industry Mathematical
    dimension
    general
    metric
    Arena rating
    rank
    300
    sample size
    422
    evaluated at
    2026-11-09T00:00:00.000Z
    source model id
    QwQ-32B-Preview
    confidence lower
    1195.1229891529651
    confidence upper
    1247.9614510184606
    Original result ↗

    LMArena

    1,218.012

    source id
    lmarena
    leaderboard name
    LMArena Text Chinese
    dimension
    general
    metric
    Arena rating
    rank
    300
    sample size
    206
    evaluated at
    2026-11-09T00:00:00.000Z
    source model id
    QwQ-32B-Preview
    confidence lower
    1177.757889600476
    confidence upper
    1258.265632455566
    Original result ↗

    Open LLM Leaderboard v2

    44.94%

    source id
    openLLMLeaderboardV2
    leaderboard name
    Open LLM v2 MATH Lvl 5 · Raw
    dimension
    math
    metric
    Raw accuracy
    rank
    302
    aggregation scope
    suite
    Open LLM v2
    co2_kg
    20.42077955247921
    status
    archived
    precision
    bfloat16
    task_count
    6
    metric_kind
    Raw accuracy
    rank_method
    Derived competition rank over published evaluations with reported scores, including variants and source flags
    weight_type
    Original
    published_at
    2025-03-20T12:17:27Z
    chat_template
    true
    suite_version
    2
    model_revision
    1032e81cb936c486aae1d33da75b2fbcd5deed4a
    source_flagged
    false
    missing_metrics
      dataset_revision
      9c09a7cae43334062a82cb164f2ef255013dafa2
      metric_population
      4576
      ranking_population
      4576
      source_flag_anomaly
      false
      source model id
      Qwen/QwQ-32B-Preview
      Original result ↗

      Open LLM Leaderboard v2

      44.94%

      source id
      openLLMLeaderboardV2
      leaderboard name
      Open LLM v2 MATH Lvl 5 · Normalized
      dimension
      math
      metric
      Normalized score
      rank
      302
      aggregation scope
      suite
      Open LLM v2
      co2_kg
      20.42077955247921
      status
      archived
      precision
      bfloat16
      task_count
      6
      metric_kind
      Normalized score
      rank_method
      Derived competition rank over published evaluations with reported scores, including variants and source flags
      weight_type
      Original
      published_at
      2025-03-20T12:17:27Z
      chat_template
      true
      suite_version
      2
      model_revision
      1032e81cb936c486aae1d33da75b2fbcd5deed4a
      source_flagged
      false
      missing_metrics
        dataset_revision
        9c09a7cae43334062a82cb164f2ef255013dafa2
        metric_population
        4576
        ranking_population
        4576
        source_flag_anomaly
        false
        source model id
        Qwen/QwQ-32B-Preview
        Original result ↗

        LMArena

        1,213.456

        source id
        lmarena
        leaderboard name
        LMArena Text Math
        dimension
        general
        metric
        Arena rating
        rank
        303
        sample size
        480
        evaluated at
        2026-11-09T00:00:00.000Z
        source model id
        QwQ-32B-Preview
        confidence lower
        1189.1334818380897
        confidence upper
        1237.7781756054387
        Original result ↗

        LMArena

        1,208.605

        source id
        lmarena
        leaderboard name
        LMArena Text Style Control Math
        dimension
        style
        metric
        Arena rating
        rank
        323
        sample size
        480
        evaluated at
        2026-11-09T00:00:00.000Z
        source model id
        QwQ-32B-Preview
        confidence lower
        1184.1528996617758
        confidence upper
        1233.0576079609946
        Original result ↗

        LMArena

        1,134.003

        source id
        lmarena
        leaderboard name
        LMArena Text Expert
        dimension
        general
        metric
        Arena rating
        rank
        325
        sample size
        232
        evaluated at
        2026-11-09T00:00:00.000Z
        source model id
        QwQ-32B-Preview
        confidence lower
        1098.3237050510083
        confidence upper
        1169.6824585299416
        Original result ↗

        LMArena

        1,215.125

        source id
        lmarena
        leaderboard name
        LMArena Text Style Control Industry Mathematical
        dimension
        style
        metric
        Arena rating
        rank
        330
        sample size
        422
        evaluated at
        2026-11-09T00:00:00.000Z
        source model id
        QwQ-32B-Preview
        confidence lower
        1188.60637893494
        confidence upper
        1241.642638794534
        Original result ↗

        LMArena

        1,233.767

        source id
        lmarena
        leaderboard name
        LMArena Text Style Control Chinese
        dimension
        style
        metric
        Arena rating
        rank
        331
        sample size
        206
        evaluated at
        2026-11-09T00:00:00.000Z
        source model id
        QwQ-32B-Preview
        confidence lower
        1193.9982085636184
        confidence upper
        1273.5364261351492
        Original result ↗

        LMArena

        1,166.526

        source id
        lmarena
        leaderboard name
        LMArena Text Longer Query
        dimension
        general
        metric
        Arena rating
        rank
        334
        sample size
        475
        evaluated at
        2026-11-09T00:00:00.000Z
        source model id
        QwQ-32B-Preview
        confidence lower
        1140.742874701691
        confidence upper
        1192.3094988481043
        Original result ↗

        LMArena

        1,155.767

        source id
        lmarena
        leaderboard name
        LMArena Text Instruction Following
        dimension
        general
        metric
        Arena rating
        rank
        335
        sample size
        1329
        evaluated at
        2026-11-09T00:00:00.000Z
        source model id
        QwQ-32B-Preview
        confidence lower
        1139.9457751881498
        confidence upper
        1171.5883744991354
        Original result ↗

        LMArena

        1,170.833

        source id
        lmarena
        leaderboard name
        LMArena Text Hard Prompts English
        dimension
        general
        metric
        Arena rating
        rank
        336
        sample size
        519
        evaluated at
        2026-11-09T00:00:00.000Z
        source model id
        QwQ-32B-Preview
        confidence lower
        1146.4155194053671
        confidence upper
        1195.250018972465
        Original result ↗

        LMArena

        1,162.395

        source id
        lmarena
        leaderboard name
        LMArena Text Hard Prompts
        dimension
        general
        metric
        Arena rating
        rank
        336
        sample size
        852
        evaluated at
        2026-11-09T00:00:00.000Z
        source model id
        QwQ-32B-Preview
        confidence lower
        1143.3172262415956
        confidence upper
        1181.471995252315
        Original result ↗

        LMArena

        1,143.099

        source id
        lmarena
        leaderboard name
        LMArena Text Industry Legal And Government
        dimension
        general
        metric
        Arena rating
        rank
        338
        sample size
        214
        evaluated at
        2026-11-09T00:00:00.000Z
        source model id
        QwQ-32B-Preview
        confidence lower
        1102.3136537393668
        confidence upper
        1183.8851293414134
        Original result ↗

        LMArena

        1,129.522

        source id
        lmarena
        leaderboard name
        LMArena Text Non English
        dimension
        general
        metric
        Arena rating
        rank
        342
        sample size
        1448
        evaluated at
        2026-11-09T00:00:00.000Z
        source model id
        QwQ-32B-Preview
        confidence lower
        1113.924392736699
        confidence upper
        1145.1205577113142
        Original result ↗

        LMArena

        1,155.076

        source id
        lmarena
        leaderboard name
        LMArena Text Coding
        dimension
        general
        metric
        Arena rating
        rank
        343
        sample size
        566
        evaluated at
        2026-11-09T00:00:00.000Z
        source model id
        QwQ-32B-Preview
        confidence lower
        1131.3815461996487
        confidence upper
        1178.7703956362209
        Original result ↗

        LMArena

        1,153.975

        source id
        lmarena
        leaderboard name
        LMArena Text Industry Life And Physical And Social Science
        dimension
        general
        metric
        Arena rating
        rank
        343
        sample size
        583
        evaluated at
        2026-11-09T00:00:00.000Z
        source model id
        QwQ-32B-Preview
        confidence lower
        1128.9489747890514
        confidence upper
        1179.0013024640925
        Original result ↗

        LMArena

        1,140.516

        source id
        lmarena
        leaderboard name
        LMArena Text Multi Turn
        dimension
        general
        metric
        Arena rating
        rank
        343
        sample size
        487
        evaluated at
        2026-11-09T00:00:00.000Z
        source model id
        QwQ-32B-Preview
        confidence lower
        1113.6347942786508
        confidence upper
        1167.397907738251
        Original result ↗

        LMArena

        1,133.618

        source id
        lmarena
        leaderboard name
        LMArena Text Creative Writing
        dimension
        general
        metric
        Arena rating
        rank
        343
        sample size
        454
        evaluated at
        2026-11-09T00:00:00.000Z
        source model id
        QwQ-32B-Preview
        confidence lower
        1105.4575250239986
        confidence upper
        1161.7784570138385
        Original result ↗

        Provider specifications & access

        1–9 / 9

        Qwen/QwQ-32B-Preview ↗

        source model id
        azure-huggingface/qwen--qwq-32b-preview@1
        hosting
        foundry-managed-compute
        platforms
        • Microsoft Foundry
        license
        apache-2.0
        context length
        32768
        architecture
        input_modalities
        • text
        output_modalities
        • text
        capabilities

          Qwen/QwQ-32B-Preview ↗

          source model id
          azure-huggingface/qwen--qwq-32b-preview@2
          hosting
          foundry-managed-compute
          platforms
          • Microsoft Foundry
          license
          apache-2.0
          context length
          32768
          architecture
          input_modalities
          • text
          output_modalities
          • text
          capabilities

            Qwen/QwQ-32B-Preview ↗

            source model id
            azure-huggingface/qwen--qwq-32b-preview@3
            hosting
            foundry-managed-compute
            platforms
            • Microsoft Foundry
            license
            apache-2.0
            context length
            32768
            architecture
            input_modalities
            • text
            output_modalities
            • text
            capabilities

              Qwen/QwQ-32B-Preview ↗

              source model id
              azure-huggingface/qwen--qwq-32b-preview@4
              hosting
              foundry-managed-compute
              platforms
              • Microsoft Foundry
              license
              apache-2.0
              context length
              32768
              architecture
              input_modalities
              • text
              output_modalities
              • text
              capabilities

                Qwen/QwQ-32B-Preview ↗

                source model id
                azure-huggingface/qwen--qwq-32b-preview@5
                hosting
                foundry-managed-compute
                platforms
                • Microsoft Foundry
                license
                apache-2.0
                context length
                32768
                architecture
                input_modalities
                • text
                output_modalities
                • text
                capabilities

                  Qwen/QwQ-32B-Preview ↗

                  source model id
                  azure-huggingface/qwen--qwq-32b-preview@6
                  hosting
                  foundry-managed-compute
                  platforms
                  • Microsoft Foundry
                  license
                  apache-2.0
                  context length
                  32768
                  architecture
                  input_modalities
                  • text
                  output_modalities
                  • text
                  capabilities

                    Qwen/QwQ-32B-Preview ↗

                    source model id
                    azure-huggingface/qwen--qwq-32b-preview@7
                    hosting
                    foundry-managed-compute
                    platforms
                    • Microsoft Foundry
                    license
                    apache-2.0
                    context length
                    32768
                    architecture
                    input_modalities
                    • text
                    output_modalities
                    • text
                    capabilities

                      Qwen/QwQ-32B-Preview ↗

                      source model id
                      HuggingFace/qwen-qwq-32b-preview@1
                      hosting
                      foundry-managed-compute
                      platforms
                      • Microsoft Foundry
                      license
                      apache-2.0
                      architecture
                      input_modalities
                      • text
                      output_modalities
                      • text
                      capabilities

                        Qwen/QwQ-32B-Preview ↗

                        source model id
                        HuggingFace/qwen-qwq-32b-preview@2
                        hosting
                        foundry-managed-compute
                        platforms
                        • Microsoft Foundry
                        license
                        apache-2.0
                        architecture
                        input_modalities
                        • text
                        output_modalities
                        • text
                        capabilities

                          Safety assessments

                          1–1 / 1

                          Foundation Model Transparency Index 2025 ↗

                          26 / 100

                          source id
                          stanfordFMTI
                          canonical model id
                          azureFoundry/azure-huggingface/qwen--qwq-32b-preview@5
                          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

                          1–7 / 7

                          azureFoundry ↗

                          field
                          context_length
                          value
                          32768
                          normalized value
                          32768
                          scope
                          source-model
                          source id
                          azureFoundry
                          confidence
                          1

                          azureFoundry ↗

                          field
                          context_length
                          value
                          32768
                          normalized value
                          32768
                          scope
                          source-model
                          source id
                          azureFoundry
                          confidence
                          1

                          azureFoundry ↗

                          field
                          context_length
                          value
                          32768
                          normalized value
                          32768
                          scope
                          source-model
                          source id
                          azureFoundry
                          confidence
                          1

                          azureFoundry ↗

                          field
                          context_length
                          value
                          32768
                          normalized value
                          32768
                          scope
                          source-model
                          source id
                          azureFoundry
                          confidence
                          1

                          azureFoundry ↗

                          field
                          context_length
                          value
                          32768
                          normalized value
                          32768
                          scope
                          source-model
                          source id
                          azureFoundry
                          confidence
                          1

                          azureFoundry ↗

                          field
                          context_length
                          value
                          32768
                          normalized value
                          32768
                          scope
                          source-model
                          source id
                          azureFoundry
                          confidence
                          1

                          azureFoundry ↗

                          field
                          context_length
                          value
                          32768
                          normalized value
                          32768
                          scope
                          source-model
                          source id
                          azureFoundry
                          confidence
                          1

                          Original sources

                          1–19 / 19

                          Hugging Face · Model repository ↗

                          Microsoft Foundry · Model page ↗

                          Microsoft Foundry · Model page ↗

                          Microsoft Foundry · Model page ↗

                          Microsoft Foundry · Model page ↗

                          Microsoft Foundry · Model page ↗

                          Microsoft Foundry · Model page ↗

                          Microsoft Foundry · Model page ↗

                          Microsoft Foundry · Model page ↗

                          Microsoft Foundry · Model page ↗

                          Microsoft Foundry · Model documentation ↗

                          GitHub · Catalog ↗

                          GitHub · Catalog ↗

                          Hugging Face · Catalog ↗

                          Hugging Face · Catalog ↗

                          LMArena · Catalog ↗

                          Microsoft Foundry · Catalog ↗

                          livebench.ai · Catalog ↗

                          livecodebench.github.io · Catalog ↗

                          Source links

                          1–8 / 8

                          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