Qwen2.5 72B Instruct

Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding an…

qwen/qwen-2.5-72b-instruct

Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...

Specifications & capabilities

Input
text
Output
text
Context window · tokens
32768
Knowledge cutoff
2024-06-30
Published model ID
Qwen2.5-72B-Instruct
Capabilities
structuredOutputs, toolCalling

Evaluations

1–20 / 76

Open LLM Leaderboard v2

86.384%

source id
openLLMLeaderboardV2
leaderboard name
Open LLM v2 IFEval · Normalized
dimension
instructionFollowing
metric
Normalized score
rank
5
aggregation scope
suite
Open LLM v2
co2_kg
47.645491341309835
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
a13fff9ad76700c7ecff2769f75943ba8395b4a7
source_flagged
false
missing_metrics
    dataset_revision
    9c09a7cae43334062a82cb164f2ef255013dafa2
    metric_population
    4576
    ranking_population
    4576
    source_flag_anomaly
    false
    source model id
    Qwen/Qwen2.5-72B-Instruct
    Original result ↗

    Open LLM Leaderboard v2

    86.384%

    source id
    openLLMLeaderboardV2
    leaderboard name
    Open LLM v2 IFEval · Raw
    dimension
    instructionFollowing
    metric
    Raw accuracy
    rank
    5
    aggregation scope
    suite
    Open LLM v2
    co2_kg
    47.645491341309835
    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
    a13fff9ad76700c7ecff2769f75943ba8395b4a7
    source_flagged
    false
    missing_metrics
      dataset_revision
      9c09a7cae43334062a82cb164f2ef255013dafa2
      metric_population
      4576
      ranking_population
      4576
      source_flag_anomaly
      false
      source model id
      Qwen/Qwen2.5-72B-Instruct
      Original result ↗

      Open LLM Leaderboard v2

      47.98%

      source id
      openLLMLeaderboardV2
      leaderboard name
      Open LLM v2 Average
      dimension
      general
      metric
      Normalized six-task average
      rank
      6
      aggregation scope
      suite
      Open LLM v2
      co2_kg
      47.645491341309835
      status
      archived
      precision
      bfloat16
      task_count
      6
      metric_kind
      Normalized six-task average
      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
      a13fff9ad76700c7ecff2769f75943ba8395b4a7
      source_flagged
      false
      missing_metrics
        dataset_revision
        9c09a7cae43334062a82cb164f2ef255013dafa2
        metric_population
        4576
        ranking_population
        4576
        source_flag_anomaly
        false
        source model id
        Qwen/Qwen2.5-72B-Instruct
        Original result ↗

        Open LLM Leaderboard v2

        59.819%

        source id
        openLLMLeaderboardV2
        leaderboard name
        Open LLM v2 MATH Lvl 5 · Raw
        dimension
        math
        metric
        Raw accuracy
        rank
        13
        aggregation scope
        suite
        Open LLM v2
        co2_kg
        47.645491341309835
        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
        a13fff9ad76700c7ecff2769f75943ba8395b4a7
        source_flagged
        false
        missing_metrics
          dataset_revision
          9c09a7cae43334062a82cb164f2ef255013dafa2
          metric_population
          4576
          ranking_population
          4576
          source_flag_anomaly
          false
          source model id
          Qwen/Qwen2.5-72B-Instruct
          Original result ↗

          Open LLM Leaderboard v2

          59.819%

          source id
          openLLMLeaderboardV2
          leaderboard name
          Open LLM v2 MATH Lvl 5 · Normalized
          dimension
          math
          metric
          Normalized score
          rank
          13
          aggregation scope
          suite
          Open LLM v2
          co2_kg
          47.645491341309835
          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
          a13fff9ad76700c7ecff2769f75943ba8395b4a7
          source_flagged
          false
          missing_metrics
            dataset_revision
            9c09a7cae43334062a82cb164f2ef255013dafa2
            metric_population
            4576
            ranking_population
            4576
            source_flag_anomaly
            false
            source model id
            Qwen/Qwen2.5-72B-Instruct
            Original result ↗

            Open LLM Leaderboard v2

            72.727%

            source id
            openLLMLeaderboardV2
            leaderboard name
            Open LLM v2 BBH · Raw
            dimension
            reasoning
            metric
            Raw accuracy
            rank
            14
            aggregation scope
            suite
            Open LLM v2
            co2_kg
            47.645491341309835
            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
            a13fff9ad76700c7ecff2769f75943ba8395b4a7
            source_flagged
            false
            missing_metrics
              dataset_revision
              9c09a7cae43334062a82cb164f2ef255013dafa2
              metric_population
              4576
              ranking_population
              4576
              source_flag_anomaly
              false
              source model id
              Qwen/Qwen2.5-72B-Instruct
              Original result ↗

              Open LLM Leaderboard v2

              61.873%

              source id
              openLLMLeaderboardV2
              leaderboard name
              Open LLM v2 BBH · Normalized
              dimension
              reasoning
              metric
              Normalized score
              rank
              15
              aggregation scope
              suite
              Open LLM v2
              co2_kg
              47.645491341309835
              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
              a13fff9ad76700c7ecff2769f75943ba8395b4a7
              source_flagged
              false
              missing_metrics
                dataset_revision
                9c09a7cae43334062a82cb164f2ef255013dafa2
                metric_population
                4576
                ranking_population
                4576
                source_flag_anomaly
                false
                source model id
                Qwen/Qwen2.5-72B-Instruct
                Original result ↗

                OpenRouter Benchmarks

                27.333%

                source id
                openRouterBenchmarks
                leaderboard name
                tau2-bench Verified Airline · Accuracy · Novita
                dimension
                agentic
                metric
                tau2-bench Verified Airline · Accuracy
                rank
                51
                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
                Novita
                attribution
                Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
                last_run_at
                2026-10-01T16:00:45.063Z
                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
                0.2733335
                accuracy_std_dev
                0.013333499999999998
                cost_per_task_usd
                0.07945186
                output_tokens_per_task
                5086.04
                latency_seconds_per_task
                632.9167199999999
                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
                52
                benchmark_evaluation
                true
                openrouter_permaslug
                qwen/qwen-2.5-72b-instruct
                source model id
                qwen/qwen-2.5-72b-instruct
                Original result ↗

                Open LLM Leaderboard v2

                56.258%

                source id
                openLLMLeaderboardV2
                leaderboard name
                Open LLM v2 MMLU-PRO · Raw
                dimension
                knowledge
                metric
                Raw accuracy
                rank
                53
                aggregation scope
                suite
                Open LLM v2
                co2_kg
                47.645491341309835
                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
                a13fff9ad76700c7ecff2769f75943ba8395b4a7
                source_flagged
                false
                missing_metrics
                  dataset_revision
                  9c09a7cae43334062a82cb164f2ef255013dafa2
                  metric_population
                  4576
                  ranking_population
                  4576
                  source_flag_anomaly
                  false
                  source model id
                  Qwen/Qwen2.5-72B-Instruct
                  Original result ↗

                  Open LLM Leaderboard v2

                  51.398%

                  source id
                  openLLMLeaderboardV2
                  leaderboard name
                  Open LLM v2 MMLU-PRO · Normalized
                  dimension
                  knowledge
                  metric
                  Normalized score
                  rank
                  53
                  aggregation scope
                  suite
                  Open LLM v2
                  co2_kg
                  47.645491341309835
                  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
                  a13fff9ad76700c7ecff2769f75943ba8395b4a7
                  source_flagged
                  false
                  missing_metrics
                    dataset_revision
                    9c09a7cae43334062a82cb164f2ef255013dafa2
                    metric_population
                    4576
                    ranking_population
                    4576
                    source_flag_anomaly
                    false
                    source model id
                    Qwen/Qwen2.5-72B-Instruct
                    Original result ↗

                    OpenRouter Benchmarks

                    46.128%

                    source id
                    openRouterBenchmarks
                    leaderboard name
                    GPQA Diamond · Accuracy · Novita
                    dimension
                    knowledge
                    metric
                    GPQA Diamond · Accuracy
                    rank
                    56
                    sample size
                    198
                    aggregation scope
                    status
                    published
                    harness
                    url
                    https://github.com/OpenRouterTeam/benchmark-harness
                    name
                    OpenRouter benchmark harness
                    direction
                    higherIsBetter
                    run_count
                    1
                    conditions
                    window
                    newest 90 days; successful visible nonzero runs
                    dataset
                    benchmark-leaderboard
                    benchmark
                    id
                    gpqa_diamond
                    name
                    GPQA Diamond
                    record_kind
                    aggregate
                    provider_name
                    Novita
                    attribution
                    Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
                    last_run_at
                    2026-10-01T16:27:00.375Z
                    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
                    198
                    source_file
                    benchmark-leaderboard.json
                    source_page
                    https://openrouter.ai/benchmarks/gpqa-diamond
                    measurements
                    accuracy
                    0.461279
                    cost_per_task_usd
                    0.0011232171717171719
                    output_tokens_per_task
                    2036.2272727272727
                    latency_seconds_per_task
                    136.7887626262626
                    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
                    59
                    benchmark_evaluation
                    true
                    openrouter_permaslug
                    qwen/qwen-2.5-72b-instruct
                    source model id
                    qwen/qwen-2.5-72b-instruct
                    Original result ↗

                    OpenRouter Benchmarks

                    25%

                    source id
                    openRouterBenchmarks
                    leaderboard name
                    tau2-bench Verified Airline · Accuracy · DeepInfra
                    dimension
                    agentic
                    metric
                    tau2-bench Verified Airline · Accuracy
                    rank
                    63
                    sample size
                    50
                    aggregation scope
                    status
                    published
                    harness
                    url
                    https://github.com/OpenRouterTeam/benchmark-harness
                    name
                    OpenRouter benchmark harness
                    direction
                    higherIsBetter
                    run_count
                    1
                    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
                    DeepInfra
                    attribution
                    Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
                    last_run_at
                    2026-09-01T12:59:14.290Z
                    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
                    50
                    source_file
                    benchmark-leaderboard.json
                    source_page
                    https://openrouter.ai/benchmarks/tau2-bench-airline
                    measurements
                    accuracy
                    0.25
                    cost_per_task_usd
                    0.0713485
                    output_tokens_per_task
                    6662.1
                    latency_seconds_per_task
                    660.5161400000001
                    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
                    63
                    benchmark_evaluation
                    true
                    openrouter_permaslug
                    qwen/qwen-2.5-72b-instruct
                    source model id
                    qwen/qwen-2.5-72b-instruct
                    Original result ↗

                    OpenRouter Benchmarks

                    47.658%

                    source id
                    openRouterBenchmarks
                    leaderboard name
                    GPQA Diamond · Accuracy · DeepInfra
                    dimension
                    knowledge
                    metric
                    GPQA Diamond · Accuracy
                    rank
                    66
                    sample size
                    306
                    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
                    DeepInfra
                    attribution
                    Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
                    last_run_at
                    2026-10-01T16:04:45.916Z
                    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
                    306
                    source_file
                    benchmark-leaderboard.json
                    source_page
                    https://openrouter.ai/benchmarks/gpqa-diamond
                    measurements
                    accuracy
                    0.4765793529411765
                    accuracy_std_dev
                    0.006944000000000006
                    cost_per_task_usd
                    0.0011232875816993464
                    output_tokens_per_task
                    2069.3627450980393
                    latency_seconds_per_task
                    126.67751307189543
                    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/qwen-2.5-72b-instruct
                    source model id
                    qwen/qwen-2.5-72b-instruct
                    Original result ↗

                    OpenRouter Benchmarks

                    45.96%

                    source id
                    openRouterBenchmarks
                    leaderboard name
                    GPQA Diamond · Accuracy · auto-routing
                    dimension
                    knowledge
                    metric
                    GPQA Diamond · Accuracy
                    rank
                    127
                    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
                    2026-10-01T16:47:11.191Z
                    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
                    0.45959600000000006
                    accuracy_std_dev
                    0.01346799999999998
                    cost_per_task_usd
                    0.0010278964646464647
                    output_tokens_per_task
                    1848.388888888889
                    latency_seconds_per_task
                    96.37995959595959
                    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/qwen-2.5-72b-instruct
                    source model id
                    qwen/qwen-2.5-72b-instruct
                    Original result ↗

                    OpenRouter Benchmarks

                    24%

                    source id
                    openRouterBenchmarks
                    leaderboard name
                    tau2-bench Verified Airline · Accuracy · auto-routing
                    dimension
                    agentic
                    metric
                    tau2-bench Verified Airline · Accuracy
                    rank
                    127
                    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
                    2026-10-01T16:00:49.856Z
                    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
                    0.24
                    accuracy_std_dev
                    0.033333
                    cost_per_task_usd
                    0.07327475
                    output_tokens_per_task
                    5322.46
                    latency_seconds_per_task
                    662.65563
                    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/qwen-2.5-72b-instruct
                    source model id
                    qwen/qwen-2.5-72b-instruct
                    Original result ↗

                    LMArena

                    1,180.059

                    source id
                    lmarena
                    leaderboard name
                    LMArena Text Japanese
                    dimension
                    general
                    metric
                    Arena rating
                    rank
                    225
                    sample size
                    788
                    evaluated at
                    2026-11-09T00:00:00.000Z
                    source model id
                    Qwen2.5-72B-Instruct
                    confidence lower
                    1158.6531936155288
                    confidence upper
                    1201.4657969507593
                    Original result ↗

                    LMArena

                    1,279.86

                    source id
                    lmarena
                    leaderboard name
                    LMArena Text French
                    dimension
                    general
                    metric
                    Arena rating
                    rank
                    229
                    sample size
                    340
                    evaluated at
                    2026-11-09T00:00:00.000Z
                    source model id
                    Qwen2.5-72B-Instruct
                    confidence lower
                    1247.1423034046695
                    confidence upper
                    1312.5769891012746
                    Original result ↗

                    LMArena

                    1,188.111

                    source id
                    lmarena
                    leaderboard name
                    LMArena Text Korean
                    dimension
                    general
                    metric
                    Arena rating
                    rank
                    231
                    sample size
                    527
                    evaluated at
                    2026-11-09T00:00:00.000Z
                    source model id
                    Qwen2.5-72B-Instruct
                    confidence lower
                    1160.29199833404
                    confidence upper
                    1215.9291698878358
                    Original result ↗

                    LMArena

                    1,210.615

                    source id
                    lmarena
                    leaderboard name
                    LMArena Text Style Control Japanese
                    dimension
                    style
                    metric
                    Arena rating
                    rank
                    235
                    sample size
                    788
                    evaluated at
                    2026-11-09T00:00:00.000Z
                    source model id
                    Qwen2.5-72B-Instruct
                    confidence lower
                    1189.1012151056216
                    confidence upper
                    1232.1290293467334
                    Original result ↗

                    LMArena

                    1,229.692

                    source id
                    lmarena
                    leaderboard name
                    LMArena Text Style Control Korean
                    dimension
                    style
                    metric
                    Arena rating
                    rank
                    236
                    sample size
                    527
                    evaluated at
                    2026-11-09T00:00:00.000Z
                    source model id
                    Qwen2.5-72B-Instruct
                    confidence lower
                    1201.6721113787376
                    confidence upper
                    1257.7119542700925
                    Original result ↗

                    Published prices

                    1–6 / 6

                    Qwen/Qwen2.5-72B-Instruct ↗

                    $0.59

                    Inference provider
                    siliconFlow
                    Platform
                    SiliconFlow
                    Unit
                    input_tokens_per_million
                    Currency
                    USD
                    Billing conditions
                    Billing label
                    Input tokens (per 1M)

                    Qwen/Qwen2.5-72B-Instruct ↗

                    $0.59

                    Inference provider
                    siliconFlow
                    Platform
                    SiliconFlow
                    Unit
                    output_tokens_per_million
                    Currency
                    USD
                    Billing conditions
                    Billing label
                    Output tokens (per 1M)

                    Provider specifications & access

                    1–2 / 2

                    Qwen/Qwen2.5-72B-Instruct ↗

                    source model id
                    HuggingFace/qwen-qwen2.5-72b-instruct@1
                    hosting
                    foundry-managed-compute
                    platforms
                    • Microsoft Foundry
                    license
                    other
                    architecture
                    input_modalities
                    • text
                    output_modalities
                    • text
                    capabilities

                      Qwen2.5-72B-Instruct ↗

                      source model id
                      Qwen/Qwen2.5-72B-Instruct
                      hosting
                      siliconflow-hosted
                      platforms
                      • SiliconFlow
                      max output tokens
                      4096
                      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/qwen-2.5-72b-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
                      16384
                      normalized value
                      16384
                      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

                      1–17 / 17

                      SiliconFlow · Model page ↗

                      Hugging Face · Model repository ↗

                      DeepInfra · Model page ↗

                      Microsoft Foundry · Model page ↗

                      OpenRouter · Model page ↗

                      SiliconFlow · Playground ↗

                      Microsoft Foundry · Model documentation ↗

                      SiliconFlow · API documentation ↗

                      DeepInfra · Catalog ↗

                      GitHub · Catalog ↗

                      GitHub · Catalog ↗

                      Hugging Face · Catalog ↗

                      LMArena · Catalog ↗

                      Microsoft Foundry · Catalog ↗

                      OpenRouter · Catalog ↗

                      OpenRouter · Catalog ↗

                      SiliconFlow · Catalog ↗

                      Source links

                      1–11 / 11

                      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