OpenAI model product
GPT-5.2
7%).
Updated Aug 12, 2026. Default version: GPT-5.2
LLMBoard score71.4GPT-5.2
Coverage100%23 benchmark families
Context window400KTokens
Official input price$1.75OpenAI API
GPT-5.2 Specifications
Technical details for the model's default version.
- Version
- GPT-5.2
- Released
- Dec 11, 2025
- Knowledge cutoff
- Aug 25, 2025
- Parameters
- N/A
- Context window
- 400K
- Max output
- 128K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
GPT-5.2 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
GPT-5.2 Benchmark Results
Benchmark scores for GPT-5.2.
| BrowseComp Long Context 128k | 0.9 | 1 | 5 | 100.0% | C | |
| BrowseComp Long Context 256k | 0.9 | 1 | 2 | 100.0% | C | |
| Graphwalks BFS <128k | 0.9 | 1 | 11 | 100.0% | C | |
| AIME 2025 | 1.0 | 2 | 114 | 99.1% | C | |
| Graphwalks parents <128k | 0.9 | 2 | 11 | 90.0% | C | |
| HMMT 2025 | 1.0 | 2 | 33 | 96.9% | C | |
| ScreenSpot Pro | 0.9 | 2 | 25 | 95.8% | C | |
| SWE-Lancer (IC-Diamond subset) | 0.7 | 3 | 6 | 60.0% | C | |
| Tau2 Telecom | 1.0 | 4 | 35 | 91.2% | C | |
| VideoMMMU | 0.9 | 4 | 26 | 88.0% | C | |
| ARC-AGI | 0.9 | 5 | 7 | 33.3% | C | |
| FrontierMath | 0.4 | 5 | 17 | 75.0% | C | |
| Tau2 Retail | 0.8 | 6 | 26 | 80.0% | C | |
| ARC-AGI v2 | 0.5 | 8 | 16 | 53.3% | C | |
| MMMLU | 0.9 | 9 | 49 | 83.3% | C | |
| GPQA | 0.9 | 13 | 234 | 94.8% | C | |
| CharXiv-R | 0.8 | 14 | 48 | 72.3% | C | |
| SWE-Bench Verified | 0.8 | 14 | 105 | 87.5% | C | |
| MMMU-Pro | 0.8 | 15 | 66 | 78.5% | C | |
| LiveBench | 0.7 | 16 | 38 | 59.5% | B | |
| Toolathlon | 0.5 | 20 | 31 | 36.7% | C | |
| MCP Atlas | 0.6 | 27 | 31 | 13.3% | C | |
| BrowseComp | 0.7 | 31 | 58 | 47.4% | C | |
| Humanity's Last Exam | 0.3 | 41 | 93 | 56.5% | C |
GPT-5.2 Arena Results
Preference and agent-evaluation results for the default version.
| search factuality | overall | 3 | 1222.7 | 52,556 | N/A | |
| search | overall | 9 | 1205.8 | 52,718 | N/A | |
| search factuality | overall | 13 | 1197.2 | 75,570 | N/A | |
| search | overall | 18 | 1172.5 | 75,752 | N/A | |
| text style control | overall | 22 | 1476.2 | 34,394 | N/A | |
| search style control | overall | 23 | 1160.5 | 52,718 | N/A | |
| vision style control | overall | 23 | 1278.4 | 15,373 | N/A | |
| search style control | overall | 28 | 1137.4 | 75,752 | N/A | |
| vision | overall | 32 | 1267.1 | 15,373 | N/A | |
| document style control | overall | 34 | 1425.7 | 28,068 | N/A | |
| document | overall | 35 | 1405.0 | 7,073 | N/A | |
| document style control | overall | 35 | 1424.4 | 7,073 | N/A | |
| document | overall | 38 | 1400.1 | 28,068 | N/A | |
| vision style control | overall | 45 | 1244.3 | 17,866 | N/A | |
| text factuality | overall | 49 | 1451.6 | 34,088 | N/A | |
| vision | overall | 51 | 1246.5 | 17,866 | N/A | |
| vision style control | overall | 54 | 1229.5 | 18,895 | N/A | |
| webdev | overall | 55 | 1417.5 | 1,057 | N/A | |
| text | overall | 60 | 1439.0 | 34,394 | N/A | |
| vision | overall | 61 | 1229.1 | 18,895 | N/A | |
| text factuality | overall | 69 | 1443.7 | 78,917 | N/A | |
| text factuality | overall | 72 | 1442.5 | 47,460 | N/A | |
| text style control | overall | 80 | 1437.4 | 47,984 | N/A | |
| text style control | overall | 82 | 1435.5 | 79,516 | N/A | |
| text | overall | 109 | 1416.3 | 47,984 | N/A | |
| text | overall | 116 | 1412.1 | 79,516 | N/A |
GPT-5.2 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $1.75 input, $14 output per 1M
- Official provider
- OpenAI
- Lowest third-party
- From $1.75 input, $14 output per 1M via Impossibl
- Tracked offerings
- 18
| Impossibl | openai/gpt-5.2 | global | $1.75 | $14 | 400K | |
| NanoGPT | openai/gpt-5.2 | global | $1.75 | $14 | 400K | |
| ZenMux | openai/gpt-5.2 | global | $1.75 | $14 | 400K | |
| Ofox | openai/gpt-5.2 | global | $1.75 | $14 | 400K | |
| OrcaRouter | openai/gpt-5.2-chat-latest | global | $1.75 | $14 | 128K | |
| OrcaRouter | openai/gpt-5.2 | global | $1.75 | $14 | 400K | |
| Kilo Gateway | openai/gpt-5.2 | global | $1.75 | $14 | 400K | |
| Merge Gateway | openai/gpt-5.2-chat-latest | global | $1.75 | $14 | 128K | |
| Merge Gateway | openai/gpt-5.2 | global | $1.75 | $14 | 400K | |
| Vercel AI Gateway | openai/gpt-5.2 | global | $1.75 | $14 | 400K | |
| OpenRouter | openai/gpt-5.2 | global | $1.75 | $14 | 400K | |
| Cloudflare AI Gateway | openai/gpt-5.2 | global | $1.75 | $14 | 400K | |
| Perplexity Agent | openai/gpt-5.2 | global | $1.75 | $14 | 400K | |
| OpenAI | gpt-5.2-chat-latest | global | $1.75 | $14 | 128K | |
| OpenAI | gpt-5.2 | global | $1.75 | $14 | 400K | |
| NEAR AI Cloud | openai/gpt-5.2 | global | $1.8 | $15.5 | 400K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
GPT-5.2 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| GPT-5.2 | 71.4 | N/A | 400K | 128K | No | Proprietary |
What is GPT-5.2?
Key information about GPT-5.2 and its available data.
7%). 75/1M input and $14/1M output tokens, with Pro variants supporting xhigh reasoning for top‑quality, end‑to‑end execution.
Data as of 2026-08-11.
GPT-5.2 vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to GPT-5.2
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
OP
GPT-5.2-Pro
OpenAI
OP
GPT-5.5-Pro
OpenAI
OP
GPT-5.6-Luna
OpenAI
OP
GPT-5.4
OpenAI
OP
GPT-5.3-Codex
OpenAI
OP
GPT-5.1
OpenAI
FAQ
Common questions about GPT-5.2.
When was GPT-5.2 released?
GPT-5.2's default version was released on Dec 11, 2025.
How much does GPT-5.2 cost?
GPT-5.2's official API price is $1.75 per million input tokens and $14 per million output tokens via OpenAI. The lowest tracked third-party offer starts at $1.75 input and $14 output via Impossibl.
Who created GPT-5.2?
GPT-5.2 was created by OpenAI.
What is the context window for GPT-5.2?
The default version has a 400K token context window.
Is GPT-5.2 open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer GPT-5.2?
18 provider offerings are linked to the default version.
What models should I compare GPT-5.2 with?
Nearby ranked alternatives include Seed 2.1 Turbo, Claude Sonnet 4.6, GPT-5.2-Pro.