OpenAI: GPT-5.2

GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamical…

openai/gpt-5.2-20251211

GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks.

Built for broad task coverage, GPT-5.2 delivers consistent gains across math, coding, sciende, and tool calling workloads, with more coherent long-form answers and improved tool-use reliability.

Specifications & capabilities

Input
file, image, text
Output
text
Context window · tokens
400000
Knowledge cutoff
2025-08-31
Capabilities
fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput, webSearch
Description source ↗

Evaluations

1–20 / 222

LMArena

1,261.467

source id
lmarena
leaderboard name
LMArena Vision Style Control Captioning
dimension
multimodal
metric
Arena rating
rank
3
sample size
92
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.2 (High)
confidence lower
1202.685295326729
confidence upper
1320.2482422243716
Original result ↗

LMArena

1,266.021

source id
lmarena
leaderboard name
LMArena Vision Captioning
dimension
multimodal
metric
Arena rating
rank
8
sample size
92
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.2 (High)
confidence lower
1206.7202514684839
confidence upper
1325.3212061476022
Original result ↗

SWE-bench

66.7%

source id
sweBench
leaderboard name
SWE-bench Multilingual
dimension
coding
metric
Resolved tasks
rank
9
sample size
300
evaluated at
2026-02-13T00:00:00.000Z
Original result ↗

LMArena

1,420.852

source id
lmarena
leaderboard name
LMArena Text Factuality German
dimension
factuality
metric
Arena rating
rank
24
sample size
713
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.2
confidence lower
1399.433243305455
confidence upper
1442.271372636747
Original result ↗

LMArena

1,232.434

source id
lmarena
leaderboard name
LMArena Vision Entity Recognition
dimension
multimodal
metric
Arena rating
rank
25
sample size
167
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.2 (High)
confidence lower
1191.0205963842202
confidence upper
1273.848229869693
Original result ↗

LMArena

1,165.683

source id
lmarena
leaderboard name
LMArena Vision Style Control Captioning
dimension
multimodal
metric
Arena rating
rank
25
sample size
106
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.2
confidence lower
1109.7811605382744
confidence upper
1221.5858148460923
Original result ↗

LMArena

1,440.76

source id
lmarena
leaderboard name
LMArena Text Factuality Polish
dimension
factuality
metric
Arena rating
rank
27
sample size
1075
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.2
confidence lower
1423.151962293192
confidence upper
1458.36707610968
Original result ↗

LMArena

1,167.57

source id
lmarena
leaderboard name
LMArena Vision Captioning
dimension
multimodal
metric
Arena rating
rank
27
sample size
106
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.2
confidence lower
1112.3523504830305
confidence upper
1222.7885899687246
Original result ↗

LMArena

1,401.527

source id
lmarena
leaderboard name
LMArena Text Factuality Korean
dimension
factuality
metric
Arena rating
rank
30
sample size
677
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.2
confidence lower
1382.8283499089298
confidence upper
1420.2261503446853
Original result ↗

LMArena

1,201.255

source id
lmarena
leaderboard name
LMArena Vision Style Control Entity Recognition
dimension
multimodal
metric
Arena rating
rank
30
sample size
167
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.2 (High)
confidence lower
1159.0635929763152
confidence upper
1243.4457034689556
Original result ↗

LMArena

1,486.183

source id
lmarena
leaderboard name
LMArena Text Factuality French
dimension
factuality
metric
Arena rating
rank
34
sample size
964
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.2 (High)
confidence lower
1468.1379836479673
confidence upper
1504.228923012639
Original result ↗

LMArena

1,418.772

source id
lmarena
leaderboard name
LMArena Text Factuality Japanese
dimension
factuality
metric
Arena rating
rank
34
sample size
485
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.2
confidence lower
1397.34556350895
confidence upper
1440.197479457413
Original result ↗

LMArena

1,171.689

source id
lmarena
leaderboard name
LMArena Vision Style Control Entity Recognition
dimension
multimodal
metric
Arena rating
rank
41
sample size
174
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.2
confidence lower
1130.3287275381608
confidence upper
1213.0497075083638
Original result ↗

LMArena

1,425.173

source id
lmarena
leaderboard name
LMArena Document Style Control Overall
dimension
productivity
metric
Arena rating
rank
42
sample size
29726
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.2
confidence lower
1419.3143532035515
confidence upper
1431.03246682686
Original result ↗

LMArena

1,375.356

source id
lmarena
leaderboard name
LMArena Text Factuality Korean
dimension
factuality
metric
Arena rating
rank
42
sample size
403
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.2 (High)
confidence lower
1350.9912727903147
confidence upper
1399.7208959818945
Original result ↗

LMArena

1,195.027

source id
lmarena
leaderboard name
LMArena Vision Entity Recognition
dimension
multimodal
metric
Arena rating
rank
42
sample size
174
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.2
confidence lower
1154.1307928704791
confidence upper
1235.924186656851
Original result ↗

LMArena

1,421.705

source id
lmarena
leaderboard name
LMArena Document Style Control Overall
dimension
productivity
metric
Arena rating
rank
43
sample size
7552
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.2 (High)
confidence lower
1412.5220332921094
confidence upper
1430.8870017396798
Original result ↗

LMArena

1,403.879

source id
lmarena
leaderboard name
LMArena Document Overall
dimension
productivity
metric
Arena rating
rank
43
sample size
7552
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.2 (High)
confidence lower
1394.651278951387
confidence upper
1413.1074386595592
Original result ↗

LMArena

1,426.142

source id
lmarena
leaderboard name
LMArena Text Factuality Polish
dimension
factuality
metric
Arena rating
rank
44
sample size
792
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.2 (High)
confidence lower
1405.6172842295969
confidence upper
1446.6675896430897
Original result ↗

LMArena

1,478.724

source id
lmarena
leaderboard name
LMArena Text Factuality French
dimension
factuality
metric
Arena rating
rank
45
sample size
2127
evaluated at
2026-11-09T00:00:00.000Z
source model id
GPT-5.2
confidence lower
1466.3134371573096
confidence upper
1491.1344739705437
Original result ↗

Published prices

1–20 / 38

gpt-5.2 ↗

$0.11

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Cached input tokens (per 1M)

gpt-5.2 ↗

$1.14

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
input_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Input tokens (per 1M)

gpt-5.2 ↗

$9.10

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
output_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Output tokens (per 1M)

openai/gpt-5.2 ↗

$0.18

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions

openai/gpt-5.2 ↗

$1.75

Inference provider
openRouter
Platform
OpenRouter
Unit
input_tokens_per_million
Currency
USD
Billing conditions

openai/gpt-5.2 ↗

$14.00

Inference provider
openRouter
Platform
OpenRouter
Unit
output_tokens_per_million
Currency
USD
Billing conditions

openai/gpt-5.2 ↗

$0.01

Inference provider
openRouter
Platform
OpenRouter
Unit
web_search
Currency
USD
Billing conditions

openai/gpt-5.2:batch ↗

$0.09

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
mode
batch

openai/gpt-5.2:batch ↗

$0.88

Inference provider
openRouter
Platform
OpenRouter
Unit
input_tokens_per_million
Currency
USD
Billing conditions
mode
batch

openai/gpt-5.2:batch ↗

$7.00

Inference provider
openRouter
Platform
OpenRouter
Unit
output_tokens_per_million
Currency
USD
Billing conditions
mode
batch

openai/gpt-5.2:batch ↗

$0.01

Inference provider
openRouter
Platform
OpenRouter
Unit
web_search
Currency
USD
Billing conditions
mode
batch

openai/gpt-5.2 ↗

$0.18

Inference provider
vercelAIGatewayCatalog
Platform
azure
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
azure | openai/gpt-5.2
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

openai/gpt-5.2 ↗

$1.75

Inference provider
vercelAIGatewayCatalog
Platform
azure
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
azure | openai/gpt-5.2
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

openai/gpt-5.2 ↗

$14.00

Inference provider
vercelAIGatewayCatalog
Platform
azure
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
azure | openai/gpt-5.2
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

openai/gpt-5.2 ↗

$0.01

Inference provider
vercelAIGatewayCatalog
Platform
azure
Unit
request
Currency
USD
Billing conditions
charge
web_search
endpoint
azure | openai/gpt-5.2
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Web search
Pricing via
Vercel AI Gateway

openai/gpt-5.2 ↗

$0.18

Inference provider
vercelAIGatewayCatalog
Platform
openai
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
openai | openai/gpt-5.2
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

openai/gpt-5.2 ↗

$0.09

Inference provider
vercelAIGatewayCatalog
Platform
openai
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
openai | openai/gpt-5.2
model_type
language
service_tier
flex
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

openai/gpt-5.2 ↗

$0.35

Inference provider
vercelAIGatewayCatalog
Platform
openai
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
openai | openai/gpt-5.2
model_type
language
service_tier
priority
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

openai/gpt-5.2 ↗

$1.75

Inference provider
vercelAIGatewayCatalog
Platform
openai
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
openai | openai/gpt-5.2
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

openai/gpt-5.2 ↗

$0.88

Inference provider
vercelAIGatewayCatalog
Platform
openai
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
openai | openai/gpt-5.2
model_type
language
service_tier
flex
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

Provider specifications & access

1–2 / 2

gpt-5.2 ↗

source model id
gpt-5.2
hosting
gateway
platforms
  • Cheaper Inference
context length
256000
max output tokens
128000
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities
  • reasoning
  • structuredOutputs
  • toolCalling
  • visionInput
  • webSearch

GPT 5.2 ↗

source model id
openai/gpt-5.2
hosting
vercel-gateway
platforms
  • Vercel AI Gateway
context length
400000
max output tokens
128000
architecture
input_modalities
  • text
  • image
  • pdf
output_modalities
  • text
capabilities
  • promptCaching
  • reasoning
  • structuredOutputs
  • toolCalling
  • visionInput
  • webSearch

Safety assessments

1–1 / 1

Foundation Model Transparency Index 2025 ↗

35 / 100

source id
stanfordFMTI
canonical model id
openai/gpt-5.2-20251211
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

1–7 / 7

openRouter ↗

field
context_length
value
400000
normalized value
400000
scope
source-model
source id
openRouter
confidence
1

openRouter ↗

field
context_length
value
400000
normalized value
400000
scope
source-model
source id
openRouter
confidence
1

vercelAIGatewayCatalog ↗

field
context_length
value
400000
normalized value
400000
scope
source-model
source id
vercelAIGatewayCatalog
confidence
1

vercelAIGatewayCatalog ↗

field
knowledge_cutoff
reported field
knowledge_cutoff
value
2025-08-31
normalized value
2025-08-31
precision
day
scope
source-model
source id
vercelAIGatewayCatalog
confidence
1

openRouter ↗

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

openRouter ↗

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

vercelAIGatewayCatalog ↗

field
max_output_tokens
value
128000
normalized value
128000
scope
source-model
source id
vercelAIGatewayCatalog
confidence
1

Original sources

1–9 / 9

OpenRouter · Model page ↗

OpenRouter · Model page ↗

Vercel AI Gateway · Model page ↗

api.cheaperinference.com · Source snapshot ↗

GitHub · Catalog ↗

LMArena · 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