OpenAI gpt-5.2 · azure-openai v2025-12-11
GPT-5.2 is engineered for enterprise agent scenarios—delivering structured, auditable outputs, reliable tool use, and governed integrations.
azureFoundry/azure-openai/gpt-5.2@2025-12-11
GPT-5.2 is engineered for enterprise agent scenarios—delivering structured, auditable outputs, reliable tool use, and governed integrations.
Specifications & capabilities
- Input
- text, image
- Output
- text
- Context window · tokens
- 400000
- Max input · tokens
- 272000
- Max output · tokens
- 128000
- Knowledge cutoff
- 2024-10
- Capabilities
- multimodal, reasoning, toolCalling, visionInput
Evaluations
1–16 / 16
75.5%
- source id
- bfcl
- leaderboard name
- BFCL Web Search
- dimension
- agentic
- metric
- Web-search accuracy
- rank
- 10
Original result ↗45.81%
- source id
- bfcl
- leaderboard name
- BFCL Memory
- dimension
- agentic
- metric
- Memory accuracy
- rank
- 13
Original result ↗55.87%
- source id
- bfcl
- leaderboard name
- BFCL Overall
- dimension
- toolUse
- metric
- Overall accuracy
- rank
- 16
Original result ↗87.26%
- source id
- bfcl
- leaderboard name
- BFCL Irrelevance Detection
- dimension
- toolUse
- metric
- Irrelevance detection
- rank
- 21
Original result ↗43.75%
- source id
- bfcl
- leaderboard name
- BFCL Multi Turn
- dimension
- agentic
- metric
- Multi-turn accuracy
- rank
- 24
Original result ↗40.5%
- source id
- bfcl
- leaderboard name
- BFCL Web Search
- dimension
- agentic
- metric
- Web-search accuracy
- rank
- 30
Original result ↗45.27%
- source id
- bfcl
- leaderboard name
- BFCL Overall
- dimension
- toolUse
- metric
- Overall accuracy
- rank
- 38
Original result ↗28.12%
- source id
- bfcl
- leaderboard name
- BFCL Multi Turn
- dimension
- agentic
- metric
- Multi-turn accuracy
- rank
- 42
Original result ↗70.39%
- source id
- bfcl
- leaderboard name
- BFCL Live
- dimension
- toolUse
- metric
- Live accuracy
- rank
- 58
Original result ↗79.42%
- source id
- bfcl
- leaderboard name
- BFCL Irrelevance Detection
- dimension
- toolUse
- metric
- Irrelevance detection
- rank
- 61
Original result ↗81.85%
- source id
- bfcl
- leaderboard name
- BFCL Non-Live AST
- dimension
- toolUse
- metric
- Non-live AST accuracy
- rank
- 67
Original result ↗75%
- source id
- bfcl
- leaderboard name
- BFCL Relevance Detection
- dimension
- toolUse
- metric
- Relevance detection
- rank
- 67
Original result ↗75%
- source id
- bfcl
- leaderboard name
- BFCL Relevance Detection
- dimension
- toolUse
- metric
- Relevance detection
- rank
- 68
Original result ↗67.14%
- source id
- bfcl
- leaderboard name
- BFCL Live
- dimension
- toolUse
- metric
- Live accuracy
- rank
- 73
Original result ↗78.29%
- source id
- bfcl
- leaderboard name
- BFCL Non-Live AST
- dimension
- toolUse
- metric
- Non-live AST accuracy
- rank
- 79
Original result ↗3.87%
- source id
- bfcl
- leaderboard name
- BFCL Memory
- dimension
- agentic
- metric
- Memory accuracy
- rank
- 92
Original result ↗Provider specifications & access
1–1 / 1
- source model id
- azure-openai/gpt-5.2@2025-12-11
- hosting
- foundry-managed-compute
- license
- custom
- context length
- 400000
- max input tokens
- 272000
- max output tokens
- 128000
Safety assessments
1–1 / 1
35 / 100
- source id
- stanfordFMTI
- canonical model id
- azureFoundry/azure-openai/gpt-5.2@2025-12-11
- 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
1–4 / 4
- field
- context_length
- value
- 400000
- normalized value
- 400000
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- max_input_tokens
- value
- 272000
- normalized value
- 272000
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- max_output_tokens
- value
- 128000
- normalized value
- 128000
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- training_data_cutoff
- value
- October 2024
- normalized value
- 2024-10
- precision
- month
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
Explore more models