Qwen2.5 Coder 32B Instruct

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvem…

qwen/qwen-2.5-coder-32b-instruct

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning**...

Specifications & capabilities

Input
text
Output
text
Context window · tokens
32768
Knowledge cutoff
2024-06-30
Published model ID
Qwen2.5-Coder-32B-Instruct
Capabilities
structuredOutputs

Evaluations

1–20 / 76

BigCode Models Leaderboard

83.2%

source id
bigCode
leaderboard name
humaneval-python
dimension
coding
metric
humaneval-python
rank
1
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
BigCode
evaluation_sequence_length
32768
metric_kind
humaneval-python
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
bigcode/bigcode-models-leaderboard/data/code_eval_board.csv
published_at
2024-11-11T20:36:38Z
source_revision
e9d7f58791a40b01c9477337f81d5d77602db07768042d96cbbb42e11a50ee09
metric_population
2
benchmark_evaluation
true
source model id
Qwen2.5-Coder-32B-Instruct
Original result ↗

BigCode Models Leaderboard

81.95%

source id
bigCode
leaderboard name
cpp
dimension
coding
metric
cpp
rank
1
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
BigCode
evaluation_sequence_length
32768
metric_kind
cpp
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
bigcode/bigcode-models-leaderboard/data/code_eval_board.csv
published_at
2024-11-11T20:36:38Z
source_revision
e9d7f58791a40b01c9477337f81d5d77602db07768042d96cbbb42e11a50ee09
metric_population
2
benchmark_evaluation
true
source model id
Qwen2.5-Coder-32B-Instruct
Original result ↗

BigCode Models Leaderboard

76.05%

source id
bigCode
leaderboard name
javascript
dimension
coding
metric
javascript
rank
1
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
BigCode
evaluation_sequence_length
32768
metric_kind
javascript
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
bigcode/bigcode-models-leaderboard/data/code_eval_board.csv
published_at
2024-11-11T20:36:38Z
source_revision
e9d7f58791a40b01c9477337f81d5d77602db07768042d96cbbb42e11a50ee09
metric_population
2
benchmark_evaluation
true
source model id
Qwen2.5-Coder-32B-Instruct
Original result ↗

BigCode Models Leaderboard

73.69%

source id
bigCode
leaderboard name
java
dimension
coding
metric
java
rank
1
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
BigCode
evaluation_sequence_length
32768
metric_kind
java
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
bigcode/bigcode-models-leaderboard/data/code_eval_board.csv
published_at
2024-11-11T20:36:38Z
source_revision
e9d7f58791a40b01c9477337f81d5d77602db07768042d96cbbb42e11a50ee09
metric_population
2
benchmark_evaluation
true
source model id
Qwen2.5-Coder-32B-Instruct
Original result ↗

BigCode Models Leaderboard

73.59%

source id
bigCode
leaderboard name
php
dimension
coding
metric
php
rank
1
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
BigCode
evaluation_sequence_length
32768
metric_kind
php
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
bigcode/bigcode-models-leaderboard/data/code_eval_board.csv
published_at
2024-11-11T20:36:38Z
source_revision
e9d7f58791a40b01c9477337f81d5d77602db07768042d96cbbb42e11a50ee09
metric_population
2
benchmark_evaluation
true
source model id
Qwen2.5-Coder-32B-Instruct
Original result ↗

BigCode Models Leaderboard

68.53%

source id
bigCode
leaderboard name
rust
dimension
coding
metric
rust
rank
1
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
BigCode
evaluation_sequence_length
32768
metric_kind
rust
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
bigcode/bigcode-models-leaderboard/data/code_eval_board.csv
published_at
2024-11-11T20:36:38Z
source_revision
e9d7f58791a40b01c9477337f81d5d77602db07768042d96cbbb42e11a50ee09
metric_population
2
benchmark_evaluation
true
source model id
Qwen2.5-Coder-32B-Instruct
Original result ↗

BigCode Models Leaderboard

63.38%

source id
bigCode
leaderboard name
Average score
dimension
coding
metric
Average score
rank
1
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
BigCode
evaluation_sequence_length
32768
metric_kind
Average score
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
bigcode/bigcode-models-leaderboard/data/code_eval_board.csv
published_at
2024-11-11T20:36:38Z
source_revision
e9d7f58791a40b01c9477337f81d5d77602db07768042d96cbbb42e11a50ee09
metric_population
2
benchmark_evaluation
true
source model id
Qwen2.5-Coder-32B-Instruct
Original result ↗

BigCode Models Leaderboard

61.54%

source id
bigCode
leaderboard name
racket
dimension
coding
metric
racket
rank
1
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
BigCode
evaluation_sequence_length
32768
metric_kind
racket
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
bigcode/bigcode-models-leaderboard/data/code_eval_board.csv
published_at
2024-11-11T20:36:38Z
source_revision
e9d7f58791a40b01c9477337f81d5d77602db07768042d96cbbb42e11a50ee09
metric_population
2
benchmark_evaluation
true
source model id
Qwen2.5-Coder-32B-Instruct
Original result ↗

BigCode Models Leaderboard

59.17%

source id
bigCode
leaderboard name
Win Rate
dimension
coding
metric
Win Rate
rank
1
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
BigCode
evaluation_sequence_length
32768
metric_kind
Win Rate
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
bigcode/bigcode-models-leaderboard/data/code_eval_board.csv
published_at
2024-11-11T20:36:38Z
source_revision
e9d7f58791a40b01c9477337f81d5d77602db07768042d96cbbb42e11a50ee09
metric_population
2
benchmark_evaluation
true
source model id
Qwen2.5-Coder-32B-Instruct
Original result ↗

BigCode Models Leaderboard

58.15%

source id
bigCode
leaderboard name
julia
dimension
coding
metric
julia
rank
1
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
BigCode
evaluation_sequence_length
32768
metric_kind
julia
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
bigcode/bigcode-models-leaderboard/data/code_eval_board.csv
published_at
2024-11-11T20:36:38Z
source_revision
e9d7f58791a40b01c9477337f81d5d77602db07768042d96cbbb42e11a50ee09
metric_population
2
benchmark_evaluation
true
source model id
Qwen2.5-Coder-32B-Instruct
Original result ↗

BigCode Models Leaderboard

52.73%

source id
bigCode
leaderboard name
r
dimension
coding
metric
r
rank
1
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
BigCode
evaluation_sequence_length
32768
metric_kind
r
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
bigcode/bigcode-models-leaderboard/data/code_eval_board.csv
published_at
2024-11-11T20:36:38Z
source_revision
e9d7f58791a40b01c9477337f81d5d77602db07768042d96cbbb42e11a50ee09
metric_population
2
benchmark_evaluation
true
source model id
Qwen2.5-Coder-32B-Instruct
Original result ↗

BigCode Models Leaderboard

58.12%

source id
bigCode
leaderboard name
swift
dimension
coding
metric
swift
rank
2
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
BigCode
evaluation_sequence_length
32768
metric_kind
swift
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
bigcode/bigcode-models-leaderboard/data/code_eval_board.csv
published_at
2024-11-11T20:36:38Z
source_revision
e9d7f58791a40b01c9477337f81d5d77602db07768042d96cbbb42e11a50ee09
metric_population
2
benchmark_evaluation
true
source model id
Qwen2.5-Coder-32B-Instruct
Original result ↗

BigCode Models Leaderboard

46.04%

source id
bigCode
leaderboard name
lua
dimension
coding
metric
lua
rank
2
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
BigCode
evaluation_sequence_length
32768
metric_kind
lua
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
bigcode/bigcode-models-leaderboard/data/code_eval_board.csv
published_at
2024-11-11T20:36:38Z
source_revision
e9d7f58791a40b01c9477337f81d5d77602db07768042d96cbbb42e11a50ee09
metric_population
2
benchmark_evaluation
true
source model id
Qwen2.5-Coder-32B-Instruct
Original result ↗

BigCode Models Leaderboard

26.98%

source id
bigCode
leaderboard name
d
dimension
coding
metric
d
rank
2
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
BigCode
evaluation_sequence_length
32768
metric_kind
d
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
bigcode/bigcode-models-leaderboard/data/code_eval_board.csv
published_at
2024-11-11T20:36:38Z
source_revision
e9d7f58791a40b01c9477337f81d5d77602db07768042d96cbbb42e11a50ee09
metric_population
2
benchmark_evaluation
true
source model id
Qwen2.5-Coder-32B-Instruct
Original result ↗

SWE-bench

38%

source id
sweBench
leaderboard name
SWE-bench Verified
dimension
coding
metric
Resolved tasks
rank
144
evaluated at
2025-06-16T00:00:00.000Z
Original result ↗

Open LLM Leaderboard v2

49.547%

source id
openLLMLeaderboardV2
leaderboard name
Open LLM v2 MATH Lvl 5 · Normalized
dimension
math
metric
Normalized score
rank
155
aggregation scope
suite
Open LLM v2
co2_kg
9.388779325959574
status
archived
precision
float16
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
false
suite_version
2
model_revision
b47205940b83b5b484577359f71ee7b88472df67
source_flagged
false
missing_metrics
    dataset_revision
    9c09a7cae43334062a82cb164f2ef255013dafa2
    metric_population
    4576
    ranking_population
    4576
    source_flag_anomaly
    false
    source model id
    Qwen/Qwen2.5-Coder-32B-Instruct
    Original result ↗

    Open LLM Leaderboard v2

    49.547%

    source id
    openLLMLeaderboardV2
    leaderboard name
    Open LLM v2 MATH Lvl 5 · Raw
    dimension
    math
    metric
    Raw accuracy
    rank
    155
    aggregation scope
    suite
    Open LLM v2
    co2_kg
    9.388779325959574
    status
    archived
    precision
    float16
    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
    false
    suite_version
    2
    model_revision
    b47205940b83b5b484577359f71ee7b88472df67
    source_flagged
    false
    missing_metrics
      dataset_revision
      9c09a7cae43334062a82cb164f2ef255013dafa2
      metric_population
      4576
      ranking_population
      4576
      source_flag_anomaly
      false
      source model id
      Qwen/Qwen2.5-Coder-32B-Instruct
      Original result ↗

      SWE-bench

      9%

      source id
      sweBench
      leaderboard name
      SWE-bench Verified
      dimension
      coding
      metric
      Resolved tasks
      rank
      174
      sample size
      500
      evaluated at
      2025-08-03T00:00:00.000Z
      Original result ↗

      Open LLM Leaderboard v2

      52.267%

      source id
      openLLMLeaderboardV2
      leaderboard name
      Open LLM v2 BBH · Normalized
      dimension
      reasoning
      metric
      Normalized score
      rank
      229
      aggregation scope
      suite
      Open LLM v2
      co2_kg
      9.388779325959574
      status
      archived
      precision
      float16
      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
      false
      suite_version
      2
      model_revision
      b47205940b83b5b484577359f71ee7b88472df67
      source_flagged
      false
      missing_metrics
        dataset_revision
        9c09a7cae43334062a82cb164f2ef255013dafa2
        metric_population
        4576
        ranking_population
        4576
        source_flag_anomaly
        false
        source model id
        Qwen/Qwen2.5-Coder-32B-Instruct
        Original result ↗

        Open LLM Leaderboard v2

        66.252%

        source id
        openLLMLeaderboardV2
        leaderboard name
        Open LLM v2 BBH · Raw
        dimension
        reasoning
        metric
        Raw accuracy
        rank
        258
        aggregation scope
        suite
        Open LLM v2
        co2_kg
        9.388779325959574
        status
        archived
        precision
        float16
        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
        false
        suite_version
        2
        model_revision
        b47205940b83b5b484577359f71ee7b88472df67
        source_flagged
        false
        missing_metrics
          dataset_revision
          9c09a7cae43334062a82cb164f2ef255013dafa2
          metric_population
          4576
          ranking_population
          4576
          source_flag_anomaly
          false
          source model id
          Qwen/Qwen2.5-Coder-32B-Instruct
          Original result ↗

          Published prices

          1–6 / 6

          @cf/qwen/qwen2.5-coder-32b-instruct ↗

          $0.66

          Inference provider
          cloudflareWorkersAI
          Platform
          Cloudflare Workers AI
          Unit
          input_tokens_per_million
          Currency
          USD
          Billing conditions
          Billing label
          per M input tokens

          @cf/qwen/qwen2.5-coder-32b-instruct ↗

          $1.00

          Inference provider
          cloudflareWorkersAI
          Platform
          Cloudflare Workers AI
          Unit
          output_tokens_per_million
          Currency
          USD
          Billing conditions
          Billing label
          per M output tokens

          Provider specifications & access

          1–5 / 5

          qwen2.5-coder-32b-instruct ↗

          source model id
          @cf/qwen/qwen2.5-coder-32b-instruct
          hosting
          cloudflare-hosted
          platforms
          • Cloudflare Workers AI
          context length
          32768
          architecture
          input_modalities
          • text
          output_modalities
          • text
          capabilities

            Qwen/Qwen2.5-Coder-32B-Instruct ↗

            source model id
            HuggingFace/qwen-qwen2.5-coder-32b-instruct@1
            hosting
            foundry-managed-compute
            platforms
            • Microsoft Foundry
            license
            apache-2.0
            architecture
            input_modalities
            • text
            output_modalities
            • text
            capabilities

              Qwen/Qwen2.5-Coder-32B-Instruct ↗

              source model id
              HuggingFace/qwen-qwen2.5-coder-32b-instruct@2
              hosting
              foundry-managed-compute
              platforms
              • Microsoft Foundry
              license
              apache-2.0
              architecture
              input_modalities
              • text
              output_modalities
              • text
              capabilities

                Qwen/Qwen2.5-Coder-32B-Instruct ↗

                source model id
                publishers/hf-qwen/models/qwen2.5-coder-32b-instruct@001
                hosting
                vertex-self-deployed
                platforms
                • Google Cloud Vertex AI
                architecture
                input_modalities
                • text
                output_modalities
                • text
                capabilities

                  Qwen2.5-Coder-32B-Instruct ↗

                  source model id
                  Qwen/Qwen2.5-Coder-32B-Instruct
                  hosting
                  siliconflow-hosted
                  platforms
                  • SiliconFlow
                  max output tokens
                  4096
                  architecture
                  input_modalities
                  • text
                  output_modalities
                  • text
                  capabilities
                  • structuredOutputs

                  Safety assessments

                  1–1 / 1

                  Foundation Model Transparency Index 2025 ↗

                  26 / 100

                  source id
                  stanfordFMTI
                  canonical model id
                  qwen/qwen-2.5-coder-32b-instruct
                  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
                  32768
                  normalized value
                  32768
                  scope
                  source-model
                  source id
                  openRouter
                  confidence
                  1

                  siliconFlow ↗

                  field
                  context_length
                  value
                  33K
                  scope
                  source-model
                  source id
                  siliconFlow
                  confidence
                  1

                  openRouter ↗

                  field
                  knowledge_cutoff
                  reported field
                  knowledge_cutoff
                  value
                  2024-06-30
                  normalized value
                  2024-06-30
                  precision
                  day
                  scope
                  source-model
                  source id
                  openRouter
                  confidence
                  1

                  openRouter ↗

                  field
                  max_output_tokens
                  value
                  29491
                  normalized value
                  29491
                  scope
                  source-model
                  source id
                  openRouter
                  confidence
                  1

                  siliconFlow ↗

                  field
                  max_output_tokens
                  value
                  4K
                  scope
                  source-model
                  source id
                  siliconFlow
                  confidence
                  1

                  Original sources

                  1–20 / 27

                  SiliconFlow · Model page ↗

                  Hugging Face · Model repository ↗

                  Cloudflare AI · Model page ↗

                  DeepInfra · Model page ↗

                  Google Cloud · Model page ↗

                  Microsoft Foundry · Model page ↗

                  Microsoft Foundry · Model page ↗

                  OpenRouter · Model page ↗

                  SiliconFlow · Playground ↗

                  Microsoft Foundry · Model documentation ↗

                  SiliconFlow · API documentation ↗

                  arXiv · Paper · 2309.00071 ↗

                  arXiv · Paper · 2407.10671 ↗

                  arXiv · Paper · 2409.12186 ↗

                  GitHub · Source snapshot ↗

                  Cloudflare AI · Catalog ↗

                  DeepInfra · Catalog ↗

                  GitHub · Catalog ↗

                  Google Cloud · Catalog ↗

                  Hugging Face · Catalog ↗

                  Source links

                  1–13 / 13

                  Hugging Face model card

                  1–1 / 1

                  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