OpenAI: GPT-4o (2024-05-13)

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while be…

openai/gpt-4o-2024-05-13

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.

For benchmarking against other models, it was briefly called ["im-also-a-good-gpt2-chatbot"](https://twitter.com/LiamFedus/status/1790064963966370209)

#multimodal

Specifications & capabilities

Input
text, image, file
Output
text
Context window · tokens
128000
Knowledge cutoff
2023-10
Capabilities
audioInput, fileInput, multimodal, structuredOutputs, toolCalling, visionInput
Description source ↗

Evaluations

21–40 / 85

LMArena

1,424.546

source id
lmarena
leaderboard name
LMArena Text Style Control Polish
dimension
style
metric
Arena rating
rank
109
sample size
166
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-4o (2024-05-13)
confidence lower
1367.5766352721155
confidence upper
1481.5146169829459
Original result ↗

LMArena

1,161.997

source id
lmarena
leaderboard name
LMArena Vision Style Control Overall
dimension
multimodal
metric
Arena rating
rank
110
sample size
23273
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-4o (2024-05-13)
confidence lower
1153.2106617363622
confidence upper
1170.782560207526
Original result ↗

LMArena

1,131.876

source id
lmarena
leaderboard name
LMArena Vision Chinese
dimension
multimodal
metric
Arena rating
rank
110
sample size
1472
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-4o (2024-05-13)
confidence lower
1093.5249743750135
confidence upper
1170.2261346621603
Original result ↗

LMArena

1,166.392

source id
lmarena
leaderboard name
LMArena Vision Style Control English
dimension
multimodal
metric
Arena rating
rank
113
sample size
14077
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-4o (2024-05-13)
confidence lower
1155.1265613388236
confidence upper
1177.6565533213961
Original result ↗

LMArena

1,146.841

source id
lmarena
leaderboard name
LMArena Vision English
dimension
multimodal
metric
Arena rating
rank
124
sample size
14077
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-4o (2024-05-13)
confidence lower
1135.547986122338
confidence upper
1158.1343499794195
Original result ↗

LMArena

1,136.517

source id
lmarena
leaderboard name
LMArena Vision Overall
dimension
multimodal
metric
Arena rating
rank
124
sample size
23273
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-4o (2024-05-13)
confidence lower
1127.714522847012
confidence upper
1145.319357166703
Original result ↗

LMArena

1,364.54

source id
lmarena
leaderboard name
LMArena Text Polish
dimension
general
metric
Arena rating
rank
165
sample size
166
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-4o (2024-05-13)
confidence lower
1308.0649575651832
confidence upper
1421.0151843556505
Original result ↗

LMArena

1,305.419

source id
lmarena
leaderboard name
LMArena Text Style Control Japanese
dimension
style
metric
Arena rating
rank
175
sample size
2674
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-4o (2024-05-13)
confidence lower
1289.7361988065018
confidence upper
1321.1008149292977
Original result ↗

LMArena

1,294.199

source id
lmarena
leaderboard name
LMArena Text Style Control Korean
dimension
style
metric
Arena rating
rank
187
sample size
3517
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-4o (2024-05-13)
confidence lower
1276.5334584886818
confidence upper
1311.8646799201586
Original result ↗

LMArena

1,257.022

source id
lmarena
leaderboard name
LMArena Text Japanese
dimension
general
metric
Arena rating
rank
187
sample size
2674
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-4o (2024-05-13)
confidence lower
1241.4990570609884
confidence upper
1272.5451552894972
Original result ↗

LMArena

1,337.866

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Entertainment And Sports And Media
dimension
style
metric
Arena rating
rank
197
sample size
17607
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-4o (2024-05-13)
confidence lower
1331.0051004131542
confidence upper
1344.7264506155789
Original result ↗

LMArena

1,337.605

source id
lmarena
leaderboard name
LMArena Text Style Control Creative Writing
dimension
style
metric
Arena rating
rank
197
sample size
16599
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-4o (2024-05-13)
confidence lower
1330.4274077784512
confidence upper
1344.7830246273063
Original result ↗

LMArena

1,329.466

source id
lmarena
leaderboard name
LMArena Text Style Control German
dimension
style
metric
Arena rating
rank
199
sample size
3573
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-4o (2024-05-13)
confidence lower
1315.7068678682185
confidence upper
1343.225535411507
Original result ↗

LMArena

1,359.546

source id
lmarena
leaderboard name
LMArena Text Style Control French
dimension
style
metric
Arena rating
rank
203
sample size
1359
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-4o (2024-05-13)
confidence lower
1338.4458225048284
confidence upper
1380.646762175378
Original result ↗

LMArena

1,345.386

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Writing And Literature And Language
dimension
style
metric
Arena rating
rank
204
sample size
29959
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-4o (2024-05-13)
confidence lower
1339.4942105996715
confidence upper
1351.2777616115993
Original result ↗

LMArena

1,233.925

source id
lmarena
leaderboard name
LMArena Text Korean
dimension
general
metric
Arena rating
rank
209
sample size
3517
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-4o (2024-05-13)
confidence lower
1216.398158388906
confidence upper
1251.4516856974383
Original result ↗

LMArena

1,341.217

source id
lmarena
leaderboard name
LMArena Text Style Control Spanish
dimension
style
metric
Arena rating
rank
211
sample size
1712
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-4o (2024-05-13)
confidence lower
1320.974716095187
confidence upper
1361.460051986641
Original result ↗

LMArena

1,371.349

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Legal And Government
dimension
style
metric
Arena rating
rank
212
sample size
6743
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-4o (2024-05-13)
confidence lower
1361.2344203252223
confidence upper
1381.4627997189436
Original result ↗

LMArena

1,282.302

source id
lmarena
leaderboard name
LMArena Text German
dimension
general
metric
Arena rating
rank
212
sample size
3573
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-4o (2024-05-13)
confidence lower
1268.586523500248
confidence upper
1296.017627670862
Original result ↗

LMArena

1,303.752

source id
lmarena
leaderboard name
LMArena Text French
dimension
general
metric
Arena rating
rank
214
sample size
1359
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-4o (2024-05-13)
confidence lower
1282.6311551379358
confidence upper
1324.872413066615
Original result ↗

Published prices

1–2 / 2

Provider specifications & access

1–1 / 1

OpenAI GPT-4o · azure-openai v2024-05-13 ↗

source model id
azure-openai/gpt-4o@2024-05-13
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
custom
context length
131072
max output tokens
4096
architecture
input_modalities
  • text
  • image
  • audio
output_modalities
  • text
capabilities

    Safety assessments

    1–1 / 1

    Foundation Model Transparency Index 2025 ↗

    35 / 100

    source id
    stanfordFMTI
    canonical model id
    openai/gpt-4o-2024-05-13
    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

    1–6 / 6

    azureFoundry ↗

    field
    context_length
    value
    131072
    normalized value
    131072
    scope
    source-model
    source id
    azureFoundry
    confidence
    1

    openRouter ↗

    field
    context_length
    value
    128000
    normalized value
    128000
    scope
    source-model
    source id
    openRouter
    confidence
    1

    openRouter ↗

    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

    azureFoundry ↗

    field
    max_output_tokens
    value
    4096
    normalized value
    4096
    scope
    source-model
    source id
    azureFoundry
    confidence
    1

    openRouter ↗

    field
    max_output_tokens
    value
    4096
    normalized value
    4096
    scope
    source-model
    source id
    openRouter
    confidence
    1

    azureFoundry ↗

    field
    knowledge_cutoff
    reported field
    training_data_cutoff
    value
    Oct 2023
    normalized value
    2023-10
    precision
    month
    scope
    source-model
    source id
    azureFoundry
    confidence
    1

    Original sources

    1–10 / 10

    Microsoft Foundry · Model page ↗

    OpenRouter · Model page ↗

    Microsoft Foundry · Model documentation ↗

    GitHub · Catalog ↗

    GitHub · Catalog ↗

    LMArena · Catalog ↗

    Microsoft Foundry · Catalog ↗

    OpenRouter · Catalog ↗

    livebench.ai · Catalog ↗

    www.swebench.com · Catalog ↗

    Source links

    1–8 / 8

    Explore more models

    Models

    Loading
    EVIDENCE / COMPARISON

    Benchmarks

    Explore every benchmark

    Loading

    These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

    Install TensorTrace