Phi-3-medium-4k-instruct

Explore Phi-3-medium-4k-instruct: model specifications, capabilities, benchmark results, platform pricing and original sources.

vertexAI/publishers/microsoft/models/phi3@phi-3-medium-4k-instruct

Specifications & capabilities

Input
text
Output
text
Published model ID
Phi-3-medium-4k-instruct

Evaluations

1–20 / 34

Open LLM Leaderboard v1

79.378%

source id
openLLMLeaderboardV1
leaderboard name
Open LLM v1 GSM8K
dimension
math
metric
Accuracy
rank
29
aggregation scope
suite
Open LLM v1
status
archived
precision
bfloat16
task_count
6
metric_kind
Accuracy
rank_method
Derived competition rank over published evaluations with reported scores, including variants and source flags
weight_type
Original
published_at
2024-06-25T14:11:42Z
chat_template
false
suite_version
1
model_revision
d27c49ed6abea9167240288dceb4ab6bca855293
source_flagged
true
missing_metrics
    dataset_revision
    791ca1c841030008c6c266562c2b88c9b7196550
    metric_population
    7260
    ranking_population
    7260
    source_flag_anomaly
    true
    evaluated at
    2024-05-27T15:40:50.000Z
    source model id
    microsoft/Phi-3-medium-4k-instruct
    Original result ↗

    Open Ko-LLM Leaderboard

    41.333

    source id
    openKoLLM
    leaderboard name
    ko_eqbench · eqbench,none
    dimension
    general
    metric
    ko_eqbench · eqbench,none
    rank
    55
    aggregation scope
    status
    published
    direction
    higherIsBetter
    conditions
    suite
    Open Ko-LLM
    language
    ko
    execution
    model_dtype
    torch.bfloat16
    num_fewshot_seeds
    1
    override_batch_size
    1
    num_few_shot_default
    0
    task_versions
    all
    2
    ko_gsm8k
    2
    ko_ifeval
    2
    ko_eqbench
    2
    ko_winogrande
    2
    kornat_common
    2
    kornat_social
    2
    kornat_helpful
    2
    kornat_harmless
    2
    ko_gpqa_diamond_zeroshot
    2
    metric_kind
    ko_eqbench · eqbench,none
    rank_method
    competition rank among reported evaluations in identical conditions, including unlinked observations
    source_file
    open-ko-llm-leaderboard/results/microsoft/Phi-3-medium-4k-instruct/result_2024-10-10 10:13:21.json
    published_at
    2025-01-12T22:16:32Z
    model_revision
    ae004ae82eb6eddc32906dfacb1d6dfea8f91996
    source_revision
    79263b00db68621dc9765e72ec588deada54cd531a2fd26b8a849eda14e14574
    metric_population
    238
    benchmark_evaluation
    true
    source model id
    microsoft/Phi-3-medium-4k-instruct
    Original result ↗

    Open LLM Leaderboard v1

    77.831%

    source id
    openLLMLeaderboardV1
    leaderboard name
    Open LLM v1 MMLU
    dimension
    knowledge
    metric
    Accuracy
    rank
    75
    aggregation scope
    suite
    Open LLM v1
    status
    archived
    precision
    bfloat16
    task_count
    6
    metric_kind
    Accuracy
    rank_method
    Derived competition rank over published evaluations with reported scores, including variants and source flags
    weight_type
    Original
    published_at
    2024-06-25T14:11:42Z
    chat_template
    false
    suite_version
    1
    model_revision
    d27c49ed6abea9167240288dceb4ab6bca855293
    source_flagged
    true
    missing_metrics
      dataset_revision
      791ca1c841030008c6c266562c2b88c9b7196550
      metric_population
      7260
      ranking_population
      7260
      source_flag_anomaly
      true
      evaluated at
      2024-05-27T15:40:50.000Z
      source model id
      microsoft/Phi-3-medium-4k-instruct
      Original result ↗

      Open Ko-LLM Leaderboard

      26.148%

      source id
      openKoLLM
      leaderboard name
      kornat_common · acc_norm,none
      dimension
      general
      metric
      kornat_common · acc_norm,none
      rank
      105
      aggregation scope
      status
      published
      direction
      higherIsBetter
      conditions
      suite
      Open Ko-LLM
      language
      ko
      execution
      model_dtype
      torch.bfloat16
      num_fewshot_seeds
      1
      override_batch_size
      1
      num_few_shot_default
      0
      task_versions
      all
      2
      ko_gsm8k
      2
      ko_ifeval
      2
      ko_eqbench
      2
      ko_winogrande
      2
      kornat_common
      2
      kornat_social
      2
      kornat_helpful
      2
      kornat_harmless
      2
      ko_gpqa_diamond_zeroshot
      2
      metric_kind
      kornat_common · acc_norm,none
      rank_method
      competition rank among reported evaluations in identical conditions, including unlinked observations
      source_file
      open-ko-llm-leaderboard/results/microsoft/Phi-3-medium-4k-instruct/result_2024-10-10 10:13:21.json
      published_at
      2025-01-12T22:16:32Z
      model_revision
      ae004ae82eb6eddc32906dfacb1d6dfea8f91996
      source_revision
      79263b00db68621dc9765e72ec588deada54cd531a2fd26b8a849eda14e14574
      metric_population
      238
      benchmark_evaluation
      true
      source model id
      microsoft/Phi-3-medium-4k-instruct
      Original result ↗

      Open Ko-LLM Leaderboard

      85.965%

      source id
      openKoLLM
      leaderboard name
      ko_eqbench · percent_parseable,none
      dimension
      general
      metric
      ko_eqbench · percent_parseable,none
      rank
      110
      aggregation scope
      status
      published
      direction
      higherIsBetter
      conditions
      suite
      Open Ko-LLM
      language
      ko
      execution
      model_dtype
      torch.bfloat16
      num_fewshot_seeds
      1
      override_batch_size
      1
      num_few_shot_default
      0
      task_versions
      all
      2
      ko_gsm8k
      2
      ko_ifeval
      2
      ko_eqbench
      2
      ko_winogrande
      2
      kornat_common
      2
      kornat_social
      2
      kornat_helpful
      2
      kornat_harmless
      2
      ko_gpqa_diamond_zeroshot
      2
      metric_kind
      ko_eqbench · percent_parseable,none
      rank_method
      competition rank among reported evaluations in identical conditions, including unlinked observations
      source_file
      open-ko-llm-leaderboard/results/microsoft/Phi-3-medium-4k-instruct/result_2024-10-10 10:13:21.json
      published_at
      2025-01-12T22:16:32Z
      model_revision
      ae004ae82eb6eddc32906dfacb1d6dfea8f91996
      source_revision
      79263b00db68621dc9765e72ec588deada54cd531a2fd26b8a849eda14e14574
      metric_population
      238
      benchmark_evaluation
      true
      source model id
      microsoft/Phi-3-medium-4k-instruct
      Original result ↗

      Open Ko-LLM Leaderboard

      50.64%

      source id
      openKoLLM
      leaderboard name
      kornat_social · A-SVA,none
      dimension
      general
      metric
      kornat_social · A-SVA,none
      rank
      115
      aggregation scope
      status
      published
      direction
      higherIsBetter
      conditions
      suite
      Open Ko-LLM
      language
      ko
      execution
      model_dtype
      torch.bfloat16
      num_fewshot_seeds
      1
      override_batch_size
      1
      num_few_shot_default
      0
      task_versions
      all
      2
      ko_gsm8k
      2
      ko_ifeval
      2
      ko_eqbench
      2
      ko_winogrande
      2
      kornat_common
      2
      kornat_social
      2
      kornat_helpful
      2
      kornat_harmless
      2
      ko_gpqa_diamond_zeroshot
      2
      metric_kind
      kornat_social · A-SVA,none
      rank_method
      competition rank among reported evaluations in identical conditions, including unlinked observations
      source_file
      open-ko-llm-leaderboard/results/microsoft/Phi-3-medium-4k-instruct/result_2024-10-10 10:13:21.json
      published_at
      2025-01-12T22:16:32Z
      model_revision
      ae004ae82eb6eddc32906dfacb1d6dfea8f91996
      source_revision
      79263b00db68621dc9765e72ec588deada54cd531a2fd26b8a849eda14e14574
      metric_population
      238
      benchmark_evaluation
      true
      source model id
      microsoft/Phi-3-medium-4k-instruct
      Original result ↗

      Open Ko-LLM Leaderboard

      63.67%

      source id
      openKoLLM
      leaderboard name
      kornat_harmless · acc_norm,none
      dimension
      general
      metric
      kornat_harmless · acc_norm,none
      rank
      123
      aggregation scope
      status
      published
      direction
      higherIsBetter
      conditions
      suite
      Open Ko-LLM
      language
      ko
      execution
      model_dtype
      torch.bfloat16
      num_fewshot_seeds
      1
      override_batch_size
      1
      num_few_shot_default
      0
      task_versions
      all
      2
      ko_gsm8k
      2
      ko_ifeval
      2
      ko_eqbench
      2
      ko_winogrande
      2
      kornat_common
      2
      kornat_social
      2
      kornat_helpful
      2
      kornat_harmless
      2
      ko_gpqa_diamond_zeroshot
      2
      metric_kind
      kornat_harmless · acc_norm,none
      rank_method
      competition rank among reported evaluations in identical conditions, including unlinked observations
      source_file
      open-ko-llm-leaderboard/results/microsoft/Phi-3-medium-4k-instruct/result_2024-10-10 10:13:21.json
      published_at
      2025-01-12T22:16:32Z
      model_revision
      ae004ae82eb6eddc32906dfacb1d6dfea8f91996
      source_revision
      79263b00db68621dc9765e72ec588deada54cd531a2fd26b8a849eda14e14574
      metric_population
      238
      benchmark_evaluation
      true
      source model id
      microsoft/Phi-3-medium-4k-instruct
      Original result ↗

      Open Ko-LLM Leaderboard

      34.818%

      source id
      openKoLLM
      leaderboard name
      ko_ifeval · prompt_level_strict_acc,none
      dimension
      general
      metric
      ko_ifeval · prompt_level_strict_acc,none
      rank
      124
      aggregation scope
      status
      published
      direction
      higherIsBetter
      conditions
      suite
      Open Ko-LLM
      language
      ko
      execution
      model_dtype
      torch.bfloat16
      num_fewshot_seeds
      1
      override_batch_size
      1
      num_few_shot_default
      0
      task_versions
      all
      2
      ko_gsm8k
      2
      ko_ifeval
      2
      ko_eqbench
      2
      ko_winogrande
      2
      kornat_common
      2
      kornat_social
      2
      kornat_helpful
      2
      kornat_harmless
      2
      ko_gpqa_diamond_zeroshot
      2
      metric_kind
      ko_ifeval · prompt_level_strict_acc,none
      rank_method
      competition rank among reported evaluations in identical conditions, including unlinked observations
      source_file
      open-ko-llm-leaderboard/results/microsoft/Phi-3-medium-4k-instruct/result_2024-10-10 10:13:21.json
      published_at
      2025-01-12T22:16:32Z
      model_revision
      ae004ae82eb6eddc32906dfacb1d6dfea8f91996
      source_revision
      79263b00db68621dc9765e72ec588deada54cd531a2fd26b8a849eda14e14574
      metric_population
      238
      benchmark_evaluation
      true
      source model id
      microsoft/Phi-3-medium-4k-instruct
      Original result ↗

      Open Ko-LLM Leaderboard

      36.842%

      source id
      openKoLLM
      leaderboard name
      ko_ifeval · prompt_level_loose_acc,none
      dimension
      general
      metric
      ko_ifeval · prompt_level_loose_acc,none
      rank
      136
      aggregation scope
      status
      published
      direction
      higherIsBetter
      conditions
      suite
      Open Ko-LLM
      language
      ko
      execution
      model_dtype
      torch.bfloat16
      num_fewshot_seeds
      1
      override_batch_size
      1
      num_few_shot_default
      0
      task_versions
      all
      2
      ko_gsm8k
      2
      ko_ifeval
      2
      ko_eqbench
      2
      ko_winogrande
      2
      kornat_common
      2
      kornat_social
      2
      kornat_helpful
      2
      kornat_harmless
      2
      ko_gpqa_diamond_zeroshot
      2
      metric_kind
      ko_ifeval · prompt_level_loose_acc,none
      rank_method
      competition rank among reported evaluations in identical conditions, including unlinked observations
      source_file
      open-ko-llm-leaderboard/results/microsoft/Phi-3-medium-4k-instruct/result_2024-10-10 10:13:21.json
      published_at
      2025-01-12T22:16:32Z
      model_revision
      ae004ae82eb6eddc32906dfacb1d6dfea8f91996
      source_revision
      79263b00db68621dc9765e72ec588deada54cd531a2fd26b8a849eda14e14574
      metric_population
      238
      benchmark_evaluation
      true
      source model id
      microsoft/Phi-3-medium-4k-instruct
      Original result ↗

      Open Ko-LLM Leaderboard

      41.246%

      source id
      openKoLLM
      leaderboard name
      ko_ifeval · inst_level_strict_acc,none
      dimension
      general
      metric
      ko_ifeval · inst_level_strict_acc,none
      rank
      140
      aggregation scope
      status
      published
      direction
      higherIsBetter
      conditions
      suite
      Open Ko-LLM
      language
      ko
      execution
      model_dtype
      torch.bfloat16
      num_fewshot_seeds
      1
      override_batch_size
      1
      num_few_shot_default
      0
      task_versions
      all
      2
      ko_gsm8k
      2
      ko_ifeval
      2
      ko_eqbench
      2
      ko_winogrande
      2
      kornat_common
      2
      kornat_social
      2
      kornat_helpful
      2
      kornat_harmless
      2
      ko_gpqa_diamond_zeroshot
      2
      metric_kind
      ko_ifeval · inst_level_strict_acc,none
      rank_method
      competition rank among reported evaluations in identical conditions, including unlinked observations
      source_file
      open-ko-llm-leaderboard/results/microsoft/Phi-3-medium-4k-instruct/result_2024-10-10 10:13:21.json
      published_at
      2025-01-12T22:16:32Z
      model_revision
      ae004ae82eb6eddc32906dfacb1d6dfea8f91996
      source_revision
      79263b00db68621dc9765e72ec588deada54cd531a2fd26b8a849eda14e14574
      metric_population
      238
      benchmark_evaluation
      true
      source model id
      microsoft/Phi-3-medium-4k-instruct
      Original result ↗

      Open Ko-LLM Leaderboard

      43.62%

      source id
      openKoLLM
      leaderboard name
      ko_ifeval · inst_level_loose_acc,none
      dimension
      general
      metric
      ko_ifeval · inst_level_loose_acc,none
      rank
      158
      aggregation scope
      status
      published
      direction
      higherIsBetter
      conditions
      suite
      Open Ko-LLM
      language
      ko
      execution
      model_dtype
      torch.bfloat16
      num_fewshot_seeds
      1
      override_batch_size
      1
      num_few_shot_default
      0
      task_versions
      all
      2
      ko_gsm8k
      2
      ko_ifeval
      2
      ko_eqbench
      2
      ko_winogrande
      2
      kornat_common
      2
      kornat_social
      2
      kornat_helpful
      2
      kornat_harmless
      2
      ko_gpqa_diamond_zeroshot
      2
      metric_kind
      ko_ifeval · inst_level_loose_acc,none
      rank_method
      competition rank among reported evaluations in identical conditions, including unlinked observations
      source_file
      open-ko-llm-leaderboard/results/microsoft/Phi-3-medium-4k-instruct/result_2024-10-10 10:13:21.json
      published_at
      2025-01-12T22:16:32Z
      model_revision
      ae004ae82eb6eddc32906dfacb1d6dfea8f91996
      source_revision
      79263b00db68621dc9765e72ec588deada54cd531a2fd26b8a849eda14e14574
      metric_population
      238
      benchmark_evaluation
      true
      source model id
      microsoft/Phi-3-medium-4k-instruct
      Original result ↗

      Open Ko-LLM Leaderboard

      47.25%

      source id
      openKoLLM
      leaderboard name
      kornat_helpful · acc_norm,none
      dimension
      general
      metric
      kornat_helpful · acc_norm,none
      rank
      168
      aggregation scope
      status
      published
      direction
      higherIsBetter
      conditions
      suite
      Open Ko-LLM
      language
      ko
      execution
      model_dtype
      torch.bfloat16
      num_fewshot_seeds
      1
      override_batch_size
      1
      num_few_shot_default
      0
      task_versions
      all
      2
      ko_gsm8k
      2
      ko_ifeval
      2
      ko_eqbench
      2
      ko_winogrande
      2
      kornat_common
      2
      kornat_social
      2
      kornat_helpful
      2
      kornat_harmless
      2
      ko_gpqa_diamond_zeroshot
      2
      metric_kind
      kornat_helpful · acc_norm,none
      rank_method
      competition rank among reported evaluations in identical conditions, including unlinked observations
      source_file
      open-ko-llm-leaderboard/results/microsoft/Phi-3-medium-4k-instruct/result_2024-10-10 10:13:21.json
      published_at
      2025-01-12T22:16:32Z
      model_revision
      ae004ae82eb6eddc32906dfacb1d6dfea8f91996
      source_revision
      79263b00db68621dc9765e72ec588deada54cd531a2fd26b8a849eda14e14574
      metric_population
      238
      benchmark_evaluation
      true
      source model id
      microsoft/Phi-3-medium-4k-instruct
      Original result ↗

      Open Ko-LLM Leaderboard

      56.433%

      source id
      openKoLLM
      leaderboard name
      ko_winogrande · acc,none
      dimension
      general
      metric
      ko_winogrande · acc,none
      rank
      185
      aggregation scope
      status
      published
      direction
      higherIsBetter
      conditions
      suite
      Open Ko-LLM
      language
      ko
      execution
      model_dtype
      torch.bfloat16
      num_fewshot_seeds
      1
      override_batch_size
      1
      num_few_shot_default
      0
      task_versions
      all
      2
      ko_gsm8k
      2
      ko_ifeval
      2
      ko_eqbench
      2
      ko_winogrande
      2
      kornat_common
      2
      kornat_social
      2
      kornat_helpful
      2
      kornat_harmless
      2
      ko_gpqa_diamond_zeroshot
      2
      metric_kind
      ko_winogrande · acc,none
      rank_method
      competition rank among reported evaluations in identical conditions, including unlinked observations
      source_file
      open-ko-llm-leaderboard/results/microsoft/Phi-3-medium-4k-instruct/result_2024-10-10 10:13:21.json
      published_at
      2025-01-12T22:16:32Z
      model_revision
      ae004ae82eb6eddc32906dfacb1d6dfea8f91996
      source_revision
      79263b00db68621dc9765e72ec588deada54cd531a2fd26b8a849eda14e14574
      metric_population
      238
      benchmark_evaluation
      true
      source model id
      microsoft/Phi-3-medium-4k-instruct
      Original result ↗

      Open Ko-LLM Leaderboard

      0%

      source id
      openKoLLM
      leaderboard name
      ko_gsm8k · exact_match,strict-match
      dimension
      general
      metric
      ko_gsm8k · exact_match,strict-match
      rank
      216
      aggregation scope
      status
      published
      direction
      higherIsBetter
      conditions
      suite
      Open Ko-LLM
      language
      ko
      execution
      model_dtype
      torch.bfloat16
      num_fewshot_seeds
      1
      override_batch_size
      1
      num_few_shot_default
      0
      task_versions
      all
      2
      ko_gsm8k
      2
      ko_ifeval
      2
      ko_eqbench
      2
      ko_winogrande
      2
      kornat_common
      2
      kornat_social
      2
      kornat_helpful
      2
      kornat_harmless
      2
      ko_gpqa_diamond_zeroshot
      2
      metric_kind
      ko_gsm8k · exact_match,strict-match
      rank_method
      competition rank among reported evaluations in identical conditions, including unlinked observations
      source_file
      open-ko-llm-leaderboard/results/microsoft/Phi-3-medium-4k-instruct/result_2024-10-10 10:13:21.json
      published_at
      2025-01-12T22:16:32Z
      model_revision
      ae004ae82eb6eddc32906dfacb1d6dfea8f91996
      source_revision
      79263b00db68621dc9765e72ec588deada54cd531a2fd26b8a849eda14e14574
      metric_population
      238
      benchmark_evaluation
      true
      source model id
      microsoft/Phi-3-medium-4k-instruct
      Original result ↗

      Open Ko-LLM Leaderboard

      20.707%

      source id
      openKoLLM
      leaderboard name
      ko_gpqa_diamond_zeroshot · acc_norm,none
      dimension
      general
      metric
      ko_gpqa_diamond_zeroshot · acc_norm,none
      rank
      217
      aggregation scope
      status
      published
      direction
      higherIsBetter
      conditions
      suite
      Open Ko-LLM
      language
      ko
      execution
      model_dtype
      torch.bfloat16
      num_fewshot_seeds
      1
      override_batch_size
      1
      num_few_shot_default
      0
      task_versions
      all
      2
      ko_gsm8k
      2
      ko_ifeval
      2
      ko_eqbench
      2
      ko_winogrande
      2
      kornat_common
      2
      kornat_social
      2
      kornat_helpful
      2
      kornat_harmless
      2
      ko_gpqa_diamond_zeroshot
      2
      metric_kind
      ko_gpqa_diamond_zeroshot · acc_norm,none
      rank_method
      competition rank among reported evaluations in identical conditions, including unlinked observations
      source_file
      open-ko-llm-leaderboard/results/microsoft/Phi-3-medium-4k-instruct/result_2024-10-10 10:13:21.json
      published_at
      2025-01-12T22:16:32Z
      model_revision
      ae004ae82eb6eddc32906dfacb1d6dfea8f91996
      source_revision
      79263b00db68621dc9765e72ec588deada54cd531a2fd26b8a849eda14e14574
      metric_population
      238
      benchmark_evaluation
      true
      source model id
      microsoft/Phi-3-medium-4k-instruct
      Original result ↗

      Open Ko-LLM Leaderboard

      0.227%

      source id
      openKoLLM
      leaderboard name
      ko_gsm8k · exact_match,flexible-extract
      dimension
      general
      metric
      ko_gsm8k · exact_match,flexible-extract
      rank
      229
      aggregation scope
      status
      published
      direction
      higherIsBetter
      conditions
      suite
      Open Ko-LLM
      language
      ko
      execution
      model_dtype
      torch.bfloat16
      num_fewshot_seeds
      1
      override_batch_size
      1
      num_few_shot_default
      0
      task_versions
      all
      2
      ko_gsm8k
      2
      ko_ifeval
      2
      ko_eqbench
      2
      ko_winogrande
      2
      kornat_common
      2
      kornat_social
      2
      kornat_helpful
      2
      kornat_harmless
      2
      ko_gpqa_diamond_zeroshot
      2
      metric_kind
      ko_gsm8k · exact_match,flexible-extract
      rank_method
      competition rank among reported evaluations in identical conditions, including unlinked observations
      source_file
      open-ko-llm-leaderboard/results/microsoft/Phi-3-medium-4k-instruct/result_2024-10-10 10:13:21.json
      published_at
      2025-01-12T22:16:32Z
      model_revision
      ae004ae82eb6eddc32906dfacb1d6dfea8f91996
      source_revision
      79263b00db68621dc9765e72ec588deada54cd531a2fd26b8a849eda14e14574
      metric_population
      238
      benchmark_evaluation
      true
      source model id
      microsoft/Phi-3-medium-4k-instruct
      Original result ↗

      Open LLM Leaderboard v2

      49.381%

      source id
      openLLMLeaderboardV2
      leaderboard name
      Open LLM v2 BBH · Normalized
      dimension
      reasoning
      metric
      Normalized score
      rank
      444
      aggregation scope
      suite
      Open LLM v2
      co2_kg
      2.9105250466587322
      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
      d194e4e74ffad5a5e193e26af25bcfc80c7f1ffc
      source_flagged
      false
      missing_metrics
        dataset_revision
        9c09a7cae43334062a82cb164f2ef255013dafa2
        metric_population
        4576
        ranking_population
        4576
        source_flag_anomaly
        false
        source model id
        microsoft/Phi-3-medium-4k-instruct
        Original result ↗

        Open LLM Leaderboard v2

        64.125%

        source id
        openLLMLeaderboardV2
        leaderboard name
        Open LLM v2 BBH · Raw
        dimension
        reasoning
        metric
        Raw accuracy
        rank
        513
        aggregation scope
        suite
        Open LLM v2
        co2_kg
        2.9105250466587322
        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
        d194e4e74ffad5a5e193e26af25bcfc80c7f1ffc
        source_flagged
        false
        missing_metrics
          dataset_revision
          9c09a7cae43334062a82cb164f2ef255013dafa2
          metric_population
          4576
          ranking_population
          4576
          source_flag_anomaly
          false
          source model id
          microsoft/Phi-3-medium-4k-instruct
          Original result ↗

          Open LLM Leaderboard v2

          46.759%

          source id
          openLLMLeaderboardV2
          leaderboard name
          Open LLM v2 MMLU-PRO · Raw
          dimension
          knowledge
          metric
          Raw accuracy
          rank
          657
          aggregation scope
          suite
          Open LLM v2
          co2_kg
          2.9105250466587322
          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
          d194e4e74ffad5a5e193e26af25bcfc80c7f1ffc
          source_flagged
          false
          missing_metrics
            dataset_revision
            9c09a7cae43334062a82cb164f2ef255013dafa2
            metric_population
            4576
            ranking_population
            4576
            source_flag_anomaly
            false
            source model id
            microsoft/Phi-3-medium-4k-instruct
            Original result ↗

            Open LLM Leaderboard v2

            40.843%

            source id
            openLLMLeaderboardV2
            leaderboard name
            Open LLM v2 MMLU-PRO · Normalized
            dimension
            knowledge
            metric
            Normalized score
            rank
            657
            aggregation scope
            suite
            Open LLM v2
            co2_kg
            2.9105250466587322
            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
            d194e4e74ffad5a5e193e26af25bcfc80c7f1ffc
            source_flagged
            false
            missing_metrics
              dataset_revision
              9c09a7cae43334062a82cb164f2ef255013dafa2
              metric_population
              4576
              ranking_population
              4576
              source_flag_anomaly
              false
              source model id
              microsoft/Phi-3-medium-4k-instruct
              Original result ↗

              Provider specifications & access

              1–2 / 2

              microsoft/Phi-3-medium-4k-instruct ↗

              source model id
              publishers/hf-microsoft/models/phi-3-medium-4k-instruct@001
              hosting
              vertex-self-deployed
              platforms
              • Google Cloud Vertex AI
              architecture
              input_modalities
              • text
              output_modalities
              • text
              capabilities

                Phi-3-medium-4k-instruct ↗

                source model id
                publishers/microsoft/models/phi3@phi-3-medium-4k-instruct
                hosting
                vertex-self-deployed
                platforms
                • Google Cloud Vertex AI
                architecture
                input_modalities
                • text
                output_modalities
                • text
                capabilities

                  Safety assessments

                  1–1 / 1

                  Foundation Model Transparency Index 2025 ↗

                  14 / 100

                  source id
                  stanfordFMTI
                  canonical model id
                  vertexAI/publishers/microsoft/models/phi3@phi-3-medium-4k-instruct
                  taxonomy
                  transparency
                  hazard category
                  transparency
                  hazard name
                  Organization transparency
                  policy area
                  xAI
                  assessment type
                  organization-level disclosure
                  metric
                  disclosure_score
                  result label
                  14 / 100
                  sample size
                  100
                  updated at
                  2026-11-09T18:08:05.227Z

                  Original sources

                  1–10 / 10

                  Hugging Face · Model repository ↗

                  Google Cloud · Model page ↗

                  Google Cloud · Model page ↗

                  Google Cloud · Model documentation ↗

                  GitHub · Catalog ↗

                  Google Cloud · Catalog ↗

                  Hugging Face · Catalog ↗

                  Hugging Face · Catalog ↗

                  Hugging Face · Catalog ↗

                  Hugging Face · Catalog ↗

                  Source links

                  1–6 / 6

                  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