OpenAI: GPT-4o

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

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
Published model ID
gpt-4o-2024-08-06
Capabilities
fileInput, multimodal, promptCaching, structuredOutputs, toolCalling, visionInput, webSearch
Description source ↗

Evaluations

1–8 / 8

SWE-bench

11.99%

source id
sweBench
leaderboard name
SWE-bench Multimodal
dimension
coding
metric
Resolved tasks
rank
16
evaluated at
2024-10-06T00:00:00.000Z
Original result ↗

SWE-bench

9.28%

source id
sweBench
leaderboard name
SWE-bench Multimodal
dimension
coding
metric
Resolved tasks
rank
18
evaluated at
2024-10-06T00:00:00.000Z
Original result ↗

OpenRouter Benchmarks

52.666%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · OpenAI
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
24
sample size
1188
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
6
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
OpenAI
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-02T23:17:37.980Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
1188
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.5266555
accuracy_std_dev
0.023895888382383546
cost_per_task_usd
0.01547567760942761
output_tokens_per_task
1354.1801346801346
latency_seconds_per_task
13.71689898989899
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
26
benchmark_evaluation
true
openrouter_permaslug
openai/gpt-4o
source model id
openai/gpt-4o
Original result ↗

OpenRouter Benchmarks

43.222%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · OpenAI
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
24
sample size
300
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
6
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
tau_bench_verified_airline
name
tau2-bench Verified Airline
record_kind
aggregate
provider_name
OpenAI
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-02T23:10:05.271Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
tau2-bench Verified Airline · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
300
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.4322221666666667
accuracy_std_dev
0.01651776073823432
cost_per_task_usd
0.21270556333333332
output_tokens_per_task
2266.36
latency_seconds_per_task
46.30506
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
27
benchmark_evaluation
true
openrouter_permaslug
openai/gpt-4o
source model id
openai/gpt-4o
Original result ↗

SWE-bench

71.2%

source id
sweBench
leaderboard name
SWE-bench Verified
dimension
coding
metric
Resolved tasks
rank
33
evaluated at
2025-07-15T00:00:00.000Z
Original result ↗

OpenRouter Benchmarks

51.684%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Azure
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
40
sample size
396
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
2
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Azure
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-01T16:28:34.286Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
396
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.5168355
accuracy_std_dev
0.005050499999999958
cost_per_task_usd
0.017194939393939394
output_tokens_per_task
1523.2777777777778
latency_seconds_per_task
13.199247474747475
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
43
benchmark_evaluation
true
openrouter_permaslug
openai/gpt-4o
source model id
openai/gpt-4o
Original result ↗

OpenRouter Benchmarks

41.667%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · auto-routing
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
118
sample size
100
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
2
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
tau_bench_verified_airline
name
tau2-bench Verified Airline
record_kind
aggregate
provider_name
auto-routing
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-01T16:01:13.623Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
tau2-bench Verified Airline · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
100
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.416667
accuracy_std_dev
0.03
cost_per_task_usd
0.19647352999999998
output_tokens_per_task
2086.91
latency_seconds_per_task
53.166019999999996
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
128
benchmark_evaluation
true
openrouter_permaslug
openai/gpt-4o
source model id
openai/gpt-4o
Original result ↗

OpenRouter Benchmarks

51.094%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · auto-routing
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
123
sample size
396
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
2
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
auto-routing
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-01T16:03:45.472Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
396
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.510943
accuracy_std_dev
0.0008420000000000094
cost_per_task_usd
0.013169762626262625
output_tokens_per_task
1121.608585858586
latency_seconds_per_task
12.925411616161616
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
132
benchmark_evaluation
true
openrouter_permaslug
openai/gpt-4o
source model id
openai/gpt-4o
Original result ↗

Published prices

41–46 / 46

openai/gpt-4o ↗

$10.00

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
output_tokens_per_million
Currency
USD
Billing conditions
model_type
language
quote_scope
gateway_catalog
billing_scope
Vercel public catalog; endpoint prices may differ
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

openai/gpt-4o ↗

$17.00

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
output_tokens_per_million
Currency
USD
Billing conditions
model_type
language
quote_scope
gateway_catalog
service_tier
fast
billing_scope
Vercel public catalog; endpoint prices may differ
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

openai/gpt-4o ↗

$17.00

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
output_tokens_per_million
Currency
USD
Billing conditions
model_type
language
quote_scope
gateway_catalog
service_tier
priority
billing_scope
Vercel public catalog; endpoint prices may differ
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

openai/gpt-4o ↗

$10.00

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
output_tokens_per_million
Currency
USD
Billing conditions
region
eu
model_type
language
quote_scope
gateway_catalog
billing_scope
Vercel public catalog; endpoint prices may differ
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

openai/gpt-4o ↗

$10.00

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
output_tokens_per_million
Currency
USD
Billing conditions
region
us
model_type
language
quote_scope
gateway_catalog
billing_scope
Vercel public catalog; endpoint prices may differ
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

openai/gpt-4o ↗

$0.01

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
request
Currency
USD
Billing conditions
charge
web_search
model_type
language
quote_scope
gateway_catalog
billing_scope
Vercel public catalog; endpoint prices may differ
Billing label
Web search
Pricing via
Vercel AI Gateway

Provider specifications & access

1–3 / 3

gpt-4o ↗

source model id
gpt-4o
hosting
gateway
platforms
  • Cheaper Inference
context length
128000
max output tokens
16384
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities
  • structuredOutputs
  • toolCalling
  • visionInput
  • webSearch

GPT-4o ↗

source model id
openai/gpt-4o
hosting
third-party
platforms
  • OpenAI
context length
128000
max output tokens
16384
architecture
input_modalities
  • text
output_modalities
  • text
capabilities

    GPT-4o ↗

    source model id
    openai/gpt-4o
    hosting
    vercel-gateway
    platforms
    • Vercel AI Gateway
    context length
    128000
    max output tokens
    16384
    architecture
    input_modalities
    • text
    • image
    • pdf
    output_modalities
    • text
    capabilities
    • promptCaching
    • structuredOutputs
    • toolCalling
    • visionInput
    • webSearch
    regions
    • eu
    • us

    Safety assessments

    1–1 / 1

    Foundation Model Transparency Index 2025 ↗

    35 / 100

    source id
    stanfordFMTI
    canonical model id
    openai/gpt-4o
    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

    1–11 / 11

    cloudflareWorkersAI ↗

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

    openRouter ↗

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

    openRouter ↗

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

    vercelAIGatewayCatalog ↗

    field
    context_length
    value
    128000
    normalized value
    128000
    scope
    source-model
    source id
    vercelAIGatewayCatalog
    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

    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

    vercelAIGatewayCatalog ↗

    field
    knowledge_cutoff
    reported field
    knowledge_cutoff
    value
    2023-10-01
    normalized value
    2023-10-01
    precision
    day
    scope
    source-model
    source id
    vercelAIGatewayCatalog
    confidence
    1

    cloudflareWorkersAI ↗

    field
    max_output_tokens
    value
    16384
    normalized value
    16384
    scope
    source-model
    source id
    cloudflareWorkersAI
    confidence
    1

    openRouter ↗

    field
    max_output_tokens
    value
    16384
    normalized value
    16384
    scope
    source-model
    source id
    openRouter
    confidence
    1

    openRouter ↗

    field
    max_output_tokens
    value
    16384
    normalized value
    16384
    scope
    source-model
    source id
    openRouter
    confidence
    1

    vercelAIGatewayCatalog ↗

    field
    max_output_tokens
    value
    16384
    normalized value
    16384
    scope
    source-model
    source id
    vercelAIGatewayCatalog
    confidence
    1

    Original sources

    1–11 / 11

    OpenRouter · Model page ↗

    OpenRouter · Model page ↗

    Vercel AI Gateway · Model page ↗

    GitHub · Source snapshot ↗

    api.cheaperinference.com · Source snapshot ↗

    Cloudflare AI · Catalog ↗

    GitHub · Catalog ↗

    OpenRouter · Catalog ↗

    OpenRouter · Catalog ↗

    Vercel AI Gateway · Catalog ↗

    www.swebench.com · Catalog ↗

    Source links

    1–7 / 7

    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