OpenAI: GPT-4o (2024-08-06)
The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introduci…
openai/gpt-4o-2024-08-06
The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/). GPT-4o ("o" for "omni") is...
Specifications & capabilities
- Input
- text, image, file
- Output
- text
- Context window · tokens
- 128000
- Knowledge cutoff
- 2023-10-31
- Capabilities
- fileInput, multimodal, promptCaching, structuredOutputs, toolCalling, visionInput
Evaluations
41–60 / 143
44.8%
- source id
- kaggleBenchmarks
- leaderboard name
- MultiLoKo Czech · EM Czech
- dimension
- reasoning
- metric
- MultiLoKo Czech · EM Czech
- rank
- 7
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 33
- name
- EM Czech
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 56
- name
- MultiLoKo Czech
- type
- INDIVIDUAL
- owner
- metaresearch
- version
- 1
- categories
- multilingual and cross-lingual capabilities
- general knowledge and reasoning
- version_id
- 42
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · metaresearch · MultiLoKo Czech
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- MultiLoKo Czech · EM Czech
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 42/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/metaresearch/multiloko-czech/versions/1
- measurements
- name
- EM Czech
- unit
- percent
- scale
- 1
- metric
- MultiLoKo Czech · EM Czech
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 0.448
- standardDeviation
- 0
- confidenceInterval
- 0.0616434068014536
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0616434068014536
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2025-06-16T00:00:00Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 0.448
- standardDeviation
- 0
- confidenceInterval
- 0.0616434068014536
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0616434068014536
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 33
- sort_order
- DESCENDING
- source_name
- EM Czech
- display_type
- percentages
- task_version
- 1
- task_display_type
- PERCENTAGES
- normalization_status
- normalized
- published_at
- 2025-07-15T11:49:31.790Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-4o-2024-08-06
- metric_population
- 51
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2025-06-16T00:00:00.000Z
- source model id
- GPT-4o
- confidence lower
- 0.3863565931985464
- confidence upper
- 0.5096434068014536
Original result ↗44%
- source id
- kaggleBenchmarks
- leaderboard name
- MultiLoKo Italian · EM Italian
- dimension
- reasoning
- metric
- MultiLoKo Italian · EM Italian
- rank
- 7
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 41
- name
- EM Italian
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 64
- name
- MultiLoKo Italian
- type
- INDIVIDUAL
- owner
- metaresearch
- version
- 1
- categories
- multilingual and cross-lingual capabilities
- general knowledge and reasoning
- version_id
- 50
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · metaresearch · MultiLoKo Italian
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- MultiLoKo Italian · EM Italian
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 50/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/metaresearch/multiloko-italian/versions/1
- measurements
- name
- EM Italian
- unit
- percent
- scale
- 1
- metric
- MultiLoKo Italian · EM Italian
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 0.44
- standardDeviation
- 0
- confidenceInterval
- 0.0615316326264477
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0615316326264477
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2025-06-16T00:00:00Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 0.44
- standardDeviation
- 0
- confidenceInterval
- 0.0615316326264477
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0615316326264477
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 41
- sort_order
- DESCENDING
- source_name
- EM Italian
- display_type
- percentages
- task_version
- 1
- task_display_type
- PERCENTAGES
- normalization_status
- normalized
- published_at
- 2025-07-15T11:49:31.790Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-4o-2024-08-06
- metric_population
- 51
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2025-06-16T00:00:00.000Z
- source model id
- GPT-4o
- confidence lower
- 0.3784683673735523
- confidence upper
- 0.5015316326264477
Original result ↗56.4%
- source id
- kaggleBenchmarks
- leaderboard name
- MultiLoKo English · EM English
- dimension
- reasoning
- metric
- MultiLoKo English · EM English
- rank
- 8
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 27
- name
- EM English
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 52
- name
- MultiLoKo English
- type
- INDIVIDUAL
- owner
- metaresearch
- version
- 1
- categories
- multilingual and cross-lingual capabilities
- general knowledge and reasoning
- version_id
- 38
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · metaresearch · MultiLoKo English
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- MultiLoKo English · EM English
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 38/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/metaresearch/multiloko-english/versions/1
- measurements
- name
- EM English
- unit
- percent
- scale
- 1
- metric
- MultiLoKo English · EM English
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 0.564
- standardDeviation
- 0
- confidenceInterval
- 0.061469670239687
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.061469670239687
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2025-06-16T00:00:00Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 0.564
- standardDeviation
- 0
- confidenceInterval
- 0.061469670239687
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.061469670239687
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 27
- sort_order
- DESCENDING
- source_name
- EM English
- display_type
- percentages
- task_version
- 1
- task_display_type
- PERCENTAGES
- normalization_status
- normalized
- published_at
- 2025-07-15T11:49:31.790Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-4o-2024-08-06
- metric_population
- 51
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2025-06-16T00:00:00.000Z
- source model id
- GPT-4o
- confidence lower
- 0.502530329760313
- confidence upper
- 0.6254696702396869
Original result ↗46%
- source id
- kaggleBenchmarks
- leaderboard name
- MultiLoKo Portuguese · EM Portuguese
- dimension
- reasoning
- metric
- MultiLoKo Portuguese · EM Portuguese
- rank
- 8
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 48
- name
- EM Portuguese
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 71
- name
- MultiLoKo Portuguese
- type
- INDIVIDUAL
- owner
- metaresearch
- version
- 1
- categories
- multilingual and cross-lingual capabilities
- general knowledge and reasoning
- version_id
- 57
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · metaresearch · MultiLoKo Portuguese
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- MultiLoKo Portuguese · EM Portuguese
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 57/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/metaresearch/multiloko-portuguese/versions/1
- measurements
- name
- EM Portuguese
- unit
- percent
- scale
- 1
- metric
- MultiLoKo Portuguese · EM Portuguese
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 0.46
- standardDeviation
- 0
- confidenceInterval
- 0.0617808504655097
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0617808504655097
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2025-06-16T00:00:00Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 0.46
- standardDeviation
- 0
- confidenceInterval
- 0.0617808504655097
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0617808504655097
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 48
- sort_order
- DESCENDING
- source_name
- EM Portuguese
- display_type
- percentages
- task_version
- 1
- task_display_type
- PERCENTAGES
- normalization_status
- normalized
- published_at
- 2025-07-15T11:49:31.790Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-4o-2024-08-06
- metric_population
- 51
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2025-06-16T00:00:00.000Z
- source model id
- GPT-4o
- confidence lower
- 0.39821914953449034
- confidence upper
- 0.5217808504655097
Original result ↗37.6%
- source id
- kaggleBenchmarks
- leaderboard name
- MultiLoKo Dutch · EM Dutch
- dimension
- reasoning
- metric
- MultiLoKo Dutch · EM Dutch
- rank
- 8
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 34
- name
- EM Dutch
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 57
- name
- MultiLoKo Dutch
- type
- INDIVIDUAL
- owner
- metaresearch
- version
- 1
- categories
- multilingual and cross-lingual capabilities
- general knowledge and reasoning
- version_id
- 43
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · metaresearch · MultiLoKo Dutch
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- MultiLoKo Dutch · EM Dutch
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 43/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/metaresearch/multiloko-dutch/versions/1
- measurements
- name
- EM Dutch
- unit
- percent
- scale
- 1
- metric
- MultiLoKo Dutch · EM Dutch
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 0.376
- standardDeviation
- 0
- confidenceInterval
- 0.0600432655456559
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0600432655456559
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2025-06-16T00:00:00Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 0.376
- standardDeviation
- 0
- confidenceInterval
- 0.0600432655456559
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0600432655456559
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 34
- sort_order
- DESCENDING
- source_name
- EM Dutch
- display_type
- percentages
- task_version
- 1
- task_display_type
- PERCENTAGES
- normalization_status
- normalized
- published_at
- 2025-07-15T11:49:31.790Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-4o-2024-08-06
- metric_population
- 51
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2025-06-16T00:00:00.000Z
- source model id
- GPT-4o
- confidence lower
- 0.3159567344543441
- confidence upper
- 0.4360432655456559
Original result ↗25.6%
- source id
- kaggleBenchmarks
- leaderboard name
- MultiLoKo Polish · EM Polish
- dimension
- reasoning
- metric
- MultiLoKo Polish · EM Polish
- rank
- 8
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 47
- name
- EM Polish
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 70
- name
- MultiLoKo Polish
- type
- INDIVIDUAL
- owner
- metaresearch
- version
- 1
- categories
- multilingual and cross-lingual capabilities
- general knowledge and reasoning
- version_id
- 56
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · metaresearch · MultiLoKo Polish
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- MultiLoKo Polish · EM Polish
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 56/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/metaresearch/multiloko-polish/versions/1
- measurements
- name
- EM Polish
- unit
- percent
- scale
- 1
- metric
- MultiLoKo Polish · EM Polish
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 0.256
- standardDeviation
- 0
- confidenceInterval
- 0.0540984144989365
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0540984144989365
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2025-06-16T00:00:00Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 0.256
- standardDeviation
- 0
- confidenceInterval
- 0.0540984144989365
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0540984144989365
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 47
- sort_order
- DESCENDING
- source_name
- EM Polish
- display_type
- percentages
- task_version
- 1
- task_display_type
- PERCENTAGES
- normalization_status
- normalized
- published_at
- 2025-07-15T11:49:31.790Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-4o-2024-08-06
- metric_population
- 51
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2025-06-16T00:00:00.000Z
- source model id
- GPT-4o
- confidence lower
- 0.20190158550106352
- confidence upper
- 0.3100984144989365
Original result ↗25.2%
- source id
- kaggleBenchmarks
- leaderboard name
- MultiLoKo Malay · EM Malay
- dimension
- reasoning
- metric
- MultiLoKo Malay · EM Malay
- rank
- 8
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 45
- name
- EM Malay
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 68
- name
- MultiLoKo Malay
- type
- INDIVIDUAL
- owner
- metaresearch
- version
- 1
- categories
- multilingual and cross-lingual capabilities
- general knowledge and reasoning
- version_id
- 54
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · metaresearch · MultiLoKo Malay
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- MultiLoKo Malay · EM Malay
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 54/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/metaresearch/multiloko-malay/versions/1
- measurements
- name
- EM Malay
- unit
- percent
- scale
- 1
- metric
- MultiLoKo Malay · EM Malay
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 0.252
- standardDeviation
- 0
- confidenceInterval
- 0.0538181984784165
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0538181984784165
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2025-06-16T00:00:00Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 0.252
- standardDeviation
- 0
- confidenceInterval
- 0.0538181984784165
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0538181984784165
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 45
- sort_order
- DESCENDING
- source_name
- EM Malay
- display_type
- percentages
- task_version
- 1
- task_display_type
- PERCENTAGES
- normalization_status
- normalized
- published_at
- 2025-07-15T11:49:31.790Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-4o-2024-08-06
- metric_population
- 51
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2025-06-16T00:00:00.000Z
- source model id
- GPT-4o
- confidence lower
- 0.1981818015215835
- confidence upper
- 0.3058181984784165
Original result ↗35.6%
- source id
- kaggleBenchmarks
- leaderboard name
- MultiLoKo Romanian · EM Romanian
- dimension
- reasoning
- metric
- MultiLoKo Romanian · EM Romanian
- rank
- 9
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 49
- name
- EM Romanian
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 72
- name
- MultiLoKo Romanian
- type
- INDIVIDUAL
- owner
- metaresearch
- version
- 1
- categories
- multilingual and cross-lingual capabilities
- general knowledge and reasoning
- version_id
- 58
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · metaresearch · MultiLoKo Romanian
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- MultiLoKo Romanian · EM Romanian
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 58/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/metaresearch/multiloko-romanian/versions/1
- measurements
- name
- EM Romanian
- unit
- percent
- scale
- 1
- metric
- MultiLoKo Romanian · EM Romanian
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 0.356
- standardDeviation
- 0
- confidenceInterval
- 0.0593534570203831
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0593534570203831
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2025-06-16T00:00:00Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 0.356
- standardDeviation
- 0
- confidenceInterval
- 0.0593534570203831
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0593534570203831
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 49
- sort_order
- DESCENDING
- source_name
- EM Romanian
- display_type
- percentages
- task_version
- 1
- task_display_type
- PERCENTAGES
- normalization_status
- normalized
- published_at
- 2025-07-15T11:49:31.790Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-4o-2024-08-06
- metric_population
- 51
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2025-06-16T00:00:00.000Z
- source model id
- GPT-4o
- confidence lower
- 0.2966465429796169
- confidence upper
- 0.41535345702038307
Original result ↗31.6%
- source id
- kaggleBenchmarks
- leaderboard name
- MultiLoKo Indonesian · EM Indonesian
- dimension
- reasoning
- metric
- MultiLoKo Indonesian · EM Indonesian
- rank
- 9
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 40
- name
- EM Indonesian
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 63
- name
- MultiLoKo Indonesian
- type
- INDIVIDUAL
- owner
- metaresearch
- version
- 1
- categories
- multilingual and cross-lingual capabilities
- general knowledge and reasoning
- version_id
- 49
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · metaresearch · MultiLoKo Indonesian
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- MultiLoKo Indonesian · EM Indonesian
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 49/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/metaresearch/multiloko-indonesian/versions/1
- measurements
- name
- EM Indonesian
- unit
- percent
- scale
- 1
- metric
- MultiLoKo Indonesian · EM Indonesian
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 0.316
- standardDeviation
- 0
- confidenceInterval
- 0.0576301405634277
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0576301405634277
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2025-06-16T00:00:00Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 0.316
- standardDeviation
- 0
- confidenceInterval
- 0.0576301405634277
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0576301405634277
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 40
- sort_order
- DESCENDING
- source_name
- EM Indonesian
- display_type
- percentages
- task_version
- 1
- task_display_type
- PERCENTAGES
- normalization_status
- normalized
- published_at
- 2025-07-15T11:49:31.790Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-4o-2024-08-06
- metric_population
- 51
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2025-06-16T00:00:00.000Z
- source model id
- GPT-4o
- confidence lower
- 0.2583698594365723
- confidence upper
- 0.3736301405634277
Original result ↗27.2%
- source id
- kaggleBenchmarks
- leaderboard name
- MultiLoKo Vietnamese · EM Vietnamese
- dimension
- reasoning
- metric
- MultiLoKo Vietnamese · EM Vietnamese
- rank
- 9
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 59
- name
- EM Vietnamese
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 82
- name
- MultiLoKo Vietnamese
- type
- INDIVIDUAL
- owner
- metaresearch
- version
- 1
- categories
- multilingual and cross-lingual capabilities
- general knowledge and reasoning
- version_id
- 68
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · metaresearch · MultiLoKo Vietnamese
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- MultiLoKo Vietnamese · EM Vietnamese
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 68/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/metaresearch/multiloko-vietnamese/versions/1
- measurements
- name
- EM Vietnamese
- unit
- percent
- scale
- 1
- metric
- MultiLoKo Vietnamese · EM Vietnamese
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 0.272
- standardDeviation
- 0
- confidenceInterval
- 0.05516050434282
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.05516050434282
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2025-06-16T00:00:00Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 0.272
- standardDeviation
- 0
- confidenceInterval
- 0.05516050434282
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.05516050434282
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 59
- sort_order
- DESCENDING
- source_name
- EM Vietnamese
- display_type
- percentages
- task_version
- 1
- task_display_type
- PERCENTAGES
- normalization_status
- normalized
- published_at
- 2025-07-15T11:49:31.790Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-4o-2024-08-06
- metric_population
- 51
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2025-06-16T00:00:00.000Z
- source model id
- GPT-4o
- confidence lower
- 0.21683949565718003
- confidence upper
- 0.32716050434282
Original result ↗40.8%
- source id
- kaggleBenchmarks
- leaderboard name
- MultiLoKo Spanish · EM Spanish
- dimension
- reasoning
- metric
- MultiLoKo Spanish · EM Spanish
- rank
- 10
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 52
- name
- EM Spanish
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 75
- name
- MultiLoKo Spanish
- type
- INDIVIDUAL
- owner
- metaresearch
- version
- 1
- categories
- multilingual and cross-lingual capabilities
- general knowledge and reasoning
- version_id
- 61
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · metaresearch · MultiLoKo Spanish
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- MultiLoKo Spanish · EM Spanish
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 61/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/metaresearch/multiloko-spanish/versions/1
- measurements
- name
- EM Spanish
- unit
- percent
- scale
- 1
- metric
- MultiLoKo Spanish · EM Spanish
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 0.408
- standardDeviation
- 0
- confidenceInterval
- 0.0609212802792317
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0609212802792317
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2025-06-16T00:00:00Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 0.408
- standardDeviation
- 0
- confidenceInterval
- 0.0609212802792317
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0609212802792317
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 52
- sort_order
- DESCENDING
- source_name
- EM Spanish
- display_type
- percentages
- task_version
- 1
- task_display_type
- PERCENTAGES
- normalization_status
- normalized
- published_at
- 2025-07-15T11:49:31.790Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-4o-2024-08-06
- metric_population
- 51
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2025-06-16T00:00:00.000Z
- source model id
- GPT-4o
- confidence lower
- 0.34707871972076826
- confidence upper
- 0.4689212802792317
Original result ↗39.6%
- source id
- kaggleBenchmarks
- leaderboard name
- MultiLoKo French · EM French
- dimension
- reasoning
- metric
- MultiLoKo French · EM French
- rank
- 10
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 36
- name
- EM French
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 59
- name
- MultiLoKo French
- type
- INDIVIDUAL
- owner
- metaresearch
- version
- 1
- categories
- multilingual and cross-lingual capabilities
- general knowledge and reasoning
- version_id
- 45
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · metaresearch · MultiLoKo French
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- MultiLoKo French · EM French
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 45/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/metaresearch/multiloko-french/versions/1
- measurements
- name
- EM French
- unit
- percent
- scale
- 1
- metric
- MultiLoKo French · EM French
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 0.396
- standardDeviation
- 0
- confidenceInterval
- 0.0606239387228808
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0606239387228808
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2025-06-16T00:00:00Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 0.396
- standardDeviation
- 0
- confidenceInterval
- 0.0606239387228808
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0606239387228808
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 36
- sort_order
- DESCENDING
- source_name
- EM French
- display_type
- percentages
- task_version
- 1
- task_display_type
- PERCENTAGES
- normalization_status
- normalized
- published_at
- 2025-07-15T11:49:31.790Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-4o-2024-08-06
- metric_population
- 51
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2025-06-16T00:00:00.000Z
- source model id
- GPT-4o
- confidence lower
- 0.3353760612771192
- confidence upper
- 0.4566239387228808
Original result ↗33.2%
- source id
- kaggleBenchmarks
- leaderboard name
- MultiLoKo Swedish · EM Swedish
- dimension
- reasoning
- metric
- MultiLoKo Swedish · EM Swedish
- rank
- 10
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 53
- name
- EM Swedish
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 76
- name
- MultiLoKo Swedish
- type
- INDIVIDUAL
- owner
- metaresearch
- version
- 1
- categories
- multilingual and cross-lingual capabilities
- general knowledge and reasoning
- version_id
- 62
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · metaresearch · MultiLoKo Swedish
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- MultiLoKo Swedish · EM Swedish
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 62/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/metaresearch/multiloko-swedish/versions/1
- measurements
- name
- EM Swedish
- unit
- percent
- scale
- 1
- metric
- MultiLoKo Swedish · EM Swedish
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 0.332
- standardDeviation
- 0
- confidenceInterval
- 0.0583761379818247
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0583761379818247
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2025-06-16T00:00:00Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 0.332
- standardDeviation
- 0
- confidenceInterval
- 0.0583761379818247
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0583761379818247
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 53
- sort_order
- DESCENDING
- source_name
- EM Swedish
- display_type
- percentages
- task_version
- 1
- task_display_type
- PERCENTAGES
- normalization_status
- normalized
- published_at
- 2025-07-15T11:49:31.790Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-4o-2024-08-06
- metric_population
- 51
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2025-06-16T00:00:00.000Z
- source model id
- GPT-4o
- confidence lower
- 0.27362386201817535
- confidence upper
- 0.3903761379818247
Original result ↗30%
- source id
- kaggleBenchmarks
- leaderboard name
- MultiLoKo Turkish · EM Turkish
- dimension
- reasoning
- metric
- MultiLoKo Turkish · EM Turkish
- rank
- 10
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 57
- name
- EM Turkish
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 80
- name
- MultiLoKo Turkish
- type
- INDIVIDUAL
- owner
- metaresearch
- version
- 1
- categories
- multilingual and cross-lingual capabilities
- general knowledge and reasoning
- version_id
- 66
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · metaresearch · MultiLoKo Turkish
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- MultiLoKo Turkish · EM Turkish
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 66/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/metaresearch/multiloko-turkish/versions/1
- measurements
- name
- EM Turkish
- unit
- percent
- scale
- 1
- metric
- MultiLoKo Turkish · EM Turkish
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 0.3
- standardDeviation
- 0
- confidenceInterval
- 0.056805153017865
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.056805153017865
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2025-06-16T00:00:00Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 0.3
- standardDeviation
- 0
- confidenceInterval
- 0.056805153017865
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.056805153017865
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 57
- sort_order
- DESCENDING
- source_name
- EM Turkish
- display_type
- percentages
- task_version
- 1
- task_display_type
- PERCENTAGES
- normalization_status
- normalized
- published_at
- 2025-07-15T11:49:31.790Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-4o-2024-08-06
- metric_population
- 51
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2025-06-16T00:00:00.000Z
- source model id
- GPT-4o
- confidence lower
- 0.243194846982135
- confidence upper
- 0.356805153017865
Original result ↗26.8%
- source id
- kaggleBenchmarks
- leaderboard name
- MultiLoKo Hebrew · EM Hebrew
- dimension
- reasoning
- metric
- MultiLoKo Hebrew · EM Hebrew
- rank
- 10
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 38
- name
- EM Hebrew
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 61
- name
- MultiLoKo Hebrew
- type
- INDIVIDUAL
- owner
- metaresearch
- version
- 1
- categories
- multilingual and cross-lingual capabilities
- general knowledge and reasoning
- version_id
- 47
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · metaresearch · MultiLoKo Hebrew
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- MultiLoKo Hebrew · EM Hebrew
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 47/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/metaresearch/multiloko-hebrew/versions/1
- measurements
- name
- EM Hebrew
- unit
- percent
- scale
- 1
- metric
- MultiLoKo Hebrew · EM Hebrew
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 0.268
- standardDeviation
- 0
- confidenceInterval
- 0.0549036255855108
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0549036255855108
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2025-06-16T00:00:00Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 0.268
- standardDeviation
- 0
- confidenceInterval
- 0.0549036255855108
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0549036255855108
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 38
- sort_order
- DESCENDING
- source_name
- EM Hebrew
- display_type
- percentages
- task_version
- 1
- task_display_type
- PERCENTAGES
- normalization_status
- normalized
- published_at
- 2025-07-15T11:49:31.790Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-4o-2024-08-06
- metric_population
- 51
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2025-06-16T00:00:00.000Z
- source model id
- GPT-4o
- confidence lower
- 0.21309637441448923
- confidence upper
- 0.32290362558551083
Original result ↗22.4%
- source id
- kaggleBenchmarks
- leaderboard name
- MultiLoKo Thai · EM Thai
- dimension
- reasoning
- metric
- MultiLoKo Thai · EM Thai
- rank
- 10
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 55
- name
- EM Thai
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 78
- name
- MultiLoKo Thai
- type
- INDIVIDUAL
- owner
- metaresearch
- version
- 1
- categories
- multilingual and cross-lingual capabilities
- general knowledge and reasoning
- version_id
- 64
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · metaresearch · MultiLoKo Thai
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- MultiLoKo Thai · EM Thai
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 64/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/metaresearch/multiloko-thai/versions/1
- measurements
- name
- EM Thai
- unit
- percent
- scale
- 1
- metric
- MultiLoKo Thai · EM Thai
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 0.224
- standardDeviation
- 0
- confidenceInterval
- 0.0516812437175552
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0516812437175552
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2025-06-16T00:00:00Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 0.224
- standardDeviation
- 0
- confidenceInterval
- 0.0516812437175552
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0516812437175552
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 55
- sort_order
- DESCENDING
- source_name
- EM Thai
- display_type
- percentages
- task_version
- 1
- task_display_type
- PERCENTAGES
- normalization_status
- normalized
- published_at
- 2025-07-15T11:49:31.790Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-4o-2024-08-06
- metric_population
- 51
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2025-06-16T00:00:00.000Z
- source model id
- GPT-4o
- confidence lower
- 0.1723187562824448
- confidence upper
- 0.2756812437175552
Original result ↗27.2%
- source id
- kaggleBenchmarks
- leaderboard name
- MultiLoKo Korean · EM Korean
- dimension
- reasoning
- metric
- MultiLoKo Korean · EM Korean
- rank
- 11
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 44
- name
- EM Korean
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 67
- name
- MultiLoKo Korean
- type
- INDIVIDUAL
- owner
- metaresearch
- version
- 1
- categories
- multilingual and cross-lingual capabilities
- general knowledge and reasoning
- version_id
- 53
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · metaresearch · MultiLoKo Korean
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- MultiLoKo Korean · EM Korean
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 53/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/metaresearch/multiloko-korean/versions/1
- measurements
- name
- EM Korean
- unit
- percent
- scale
- 1
- metric
- MultiLoKo Korean · EM Korean
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 0.272
- standardDeviation
- 0
- confidenceInterval
- 0.05516050434282
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.05516050434282
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2025-06-16T00:00:00Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 0.272
- standardDeviation
- 0
- confidenceInterval
- 0.05516050434282
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.05516050434282
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 44
- sort_order
- DESCENDING
- source_name
- EM Korean
- display_type
- percentages
- task_version
- 1
- task_display_type
- PERCENTAGES
- normalization_status
- normalized
- published_at
- 2025-07-15T11:49:31.790Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-4o-2024-08-06
- metric_population
- 51
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2025-06-16T00:00:00.000Z
- source model id
- GPT-4o
- confidence lower
- 0.21683949565718003
- confidence upper
- 0.32716050434282
Original result ↗24%
- source id
- kaggleBenchmarks
- leaderboard name
- MultiLoKo Arabic · EM Arabic
- dimension
- reasoning
- metric
- MultiLoKo Arabic · EM Arabic
- rank
- 11
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 30
- name
- EM Arabic
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 53
- name
- MultiLoKo Arabic
- type
- INDIVIDUAL
- owner
- metaresearch
- version
- 1
- categories
- multilingual and cross-lingual capabilities
- general knowledge and reasoning
- version_id
- 39
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · metaresearch · MultiLoKo Arabic
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- MultiLoKo Arabic · EM Arabic
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 39/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/metaresearch/multiloko-arabic/versions/1
- measurements
- name
- EM Arabic
- unit
- percent
- scale
- 1
- metric
- MultiLoKo Arabic · EM Arabic
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 0.24
- standardDeviation
- 0
- confidenceInterval
- 0.0529408004810886
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0529408004810886
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2025-06-16T00:00:00Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 0.24
- standardDeviation
- 0
- confidenceInterval
- 0.0529408004810886
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0529408004810886
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 30
- sort_order
- DESCENDING
- source_name
- EM Arabic
- display_type
- percentages
- task_version
- 1
- task_display_type
- PERCENTAGES
- normalization_status
- normalized
- published_at
- 2025-07-15T11:49:31.790Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-4o-2024-08-06
- metric_population
- 51
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2025-06-16T00:00:00.000Z
- source model id
- GPT-4o
- confidence lower
- 0.1870591995189114
- confidence upper
- 0.2929408004810886
Original result ↗16.4%
- source id
- kaggleBenchmarks
- leaderboard name
- MultiLoKo Farsi · EM Farsi
- dimension
- reasoning
- metric
- MultiLoKo Farsi · EM Farsi
- rank
- 11
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 35
- name
- EM Farsi
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 58
- name
- MultiLoKo Farsi
- type
- INDIVIDUAL
- owner
- metaresearch
- version
- 1
- categories
- multilingual and cross-lingual capabilities
- general knowledge and reasoning
- version_id
- 44
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · metaresearch · MultiLoKo Farsi
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- MultiLoKo Farsi · EM Farsi
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 44/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/metaresearch/multiloko-farsi/versions/1
- measurements
- name
- EM Farsi
- unit
- percent
- scale
- 1
- metric
- MultiLoKo Farsi · EM Farsi
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 0.164
- standardDeviation
- 0
- confidenceInterval
- 0.0458989921524404
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0458989921524404
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2025-06-16T00:00:00Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 0.164
- standardDeviation
- 0
- confidenceInterval
- 0.0458989921524404
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.0458989921524404
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 35
- sort_order
- DESCENDING
- source_name
- EM Farsi
- display_type
- percentages
- task_version
- 1
- task_display_type
- PERCENTAGES
- normalization_status
- normalized
- published_at
- 2025-07-15T11:49:31.790Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-4o-2024-08-06
- metric_population
- 50
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2025-06-16T00:00:00.000Z
- source model id
- GPT-4o
- confidence lower
- 0.11810100784755961
- confidence upper
- 0.2098989921524404
Original result ↗39.2%
- source id
- kaggleBenchmarks
- leaderboard name
- MultiLoKo Tagalog · EM Tagalog
- dimension
- reasoning
- metric
- MultiLoKo Tagalog · EM Tagalog
- rank
- 12
- aggregation scope
- kaggle
- true
- status
- published
- license
- Apache-2.0
- direction
- higherIsBetter
- conditions
- task
- id
- 54
- name
- EM Tagalog
- version
- 1
- sort_order
- DESCENDING
- display_type
- percentages
- benchmark
- id
- 77
- name
- MultiLoKo Tagalog
- type
- INDIVIDUAL
- owner
- metaresearch
- version
- 1
- categories
- multilingual and cross-lingual capabilities
- general knowledge and reasoning
- version_id
- 63
- maintainer_tier
- Kaggle-maintained
- maintenance_level
- KAGGLE_MAINTAINED
- candidate
- candidate_class
- modelVersion
- record_kind
- aggregate
- attribution
- Kaggle · metaresearch · MultiLoKo Tagalog
- license_url
- https://www.apache.org/licenses/LICENSE-2.0
- metric_kind
- MultiLoKo Tagalog · EM Tagalog
- rank_method
- competition rank among reported evaluations in identical conditions, including unlinked observations
- source_file
- 63/leaderboard.json
- source_page
- https://www.kaggle.com/benchmarks/metaresearch/multiloko-tagalog/versions/1
- measurements
- name
- EM Tagalog
- unit
- percent
- scale
- 1
- metric
- MultiLoKo Tagalog · EM Tagalog
- result
- resultCase
- numericResult
- booleanResult
- false
- numericResult
- value
- 0.392
- standardDeviation
- 0
- confidenceInterval
- 0.06051637561814
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.06051637561814
- hasUnevenConfidenceInterval
- false
- taskVersionId
- 0
- evaluationDate
- 2025-06-16T00:00:00Z
- hasBooleanResult
- false
- hasNumericResult
- true
- hasTaskVersionId
- false
- hasEvaluationDate
- true
- numericResultNullable
- value
- 0.392
- standardDeviation
- 0
- confidenceInterval
- 0.06051637561814
- hasStandardDeviation
- false
- hasConfidenceInterval
- true
- confidenceIntervalNullable
- 0.06051637561814
- hasUnevenConfidenceInterval
- false
- hasNumericResultPublic
- false
- hasNumericResultPrivate
- false
- task_id
- 54
- sort_order
- DESCENDING
- source_name
- EM Tagalog
- display_type
- percentages
- task_version
- 1
- task_display_type
- PERCENTAGES
- normalization_status
- normalized
- published_at
- 2025-07-15T11:49:31.790Z
- candidate_class
- modelVersion
- source_revision
- b32d007df5acbddafca23c7dd2beba8221c519cf7dd3445a1d7bc28740ffd0d8
- publisher_anchor
- openai/gpt-4o-2024-08-06
- metric_population
- 51
- benchmark_evaluation
- true
- task_metadata_source
- benchmarkVersion
- candidate_metadata_source
- benchmarkVersionMappings
- evaluated at
- 2025-06-16T00:00:00.000Z
- source model id
- GPT-4o
- confidence lower
- 0.33148362438186
- confidence upper
- 0.45251637561814
Original result ↗Published prices
1–3 / 3
$1.25
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- cache_read_tokens_per_million
- Currency
- USD
$2.50
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- input_tokens_per_million
- Currency
- USD
$10.00
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- output_tokens_per_million
- Currency
- USD
Safety assessments
1–1 / 1
35 / 100
- source id
- stanfordFMTI
- canonical model id
- openai/gpt-4o-2024-08-06
- taxonomy
- transparency
- hazard category
- transparency
- hazard name
- Organization transparency
- policy area
- OpenAI
- assessment type
- organization-level disclosure
- metric
- disclosure_score
- result label
- 35 / 100
- sample size
- 100
- updated at
- 2026-11-09T18:08:05.227Z
Source specification observations
1–3 / 3
- field
- context_length
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2023-10-31
- normalized value
- 2023-10-31
- precision
- day
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 16384
- normalized value
- 16384
- scope
- source-model
- source id
- openRouter
- confidence
- 1
Explore more models