GPT-5.2 Pro
GPT-5.2 Pro is behind the leaders in reasoning and math. Too few results yet to rate coding, agentic tasks, safety, long context, multimodal tasks, multilingual tasks, instruction following, or factuality.
Capability profile
Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.
Too few results yet to rate Coding, Agentic, Safety, Long Context, Multimodal, Multilingual, Instruction Following or Factuality.
Price
$21.00input$168.00outputper million tokens
From openai · All prices
Evidence
15results on11benchmarks
- 9 independently verified
- 6 vendor-reported
From 6 sources · latest Oct 6, 2026 · How verification works
API features
Tool callingStructured outputsReasoning
As listed by OpenRouter
Research
1 paper reference GPT-5.2 ProGPT-5.2 Pro benchmark results
15 results on 11 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
29.0% behind the leader4 of 6 ranked benchmarks measured
- GPQA Diamond93.20Oct 6, 2026GPQA
- 57.40May 10, 2026
- ARC-AGI-254.20Oct 6, 2026ARC-AGI v2
- 36.60Oct 6, 2026
29.2% behind the leader2 of 5 ranked benchmarks measured
- 74.00Sep 9, 2026
- 46.00Sep 8, 2026
0 of 7 ranked benchmarks measured
- 77.90Oct 6, 2026
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- 90.50Sep 21, 2026
- 85.67Sep 21, 2026
- frontiermath_tier_4_v131.30May 20, 2026frontiermath_tier_4
- 81.17May 10, 2026
- 100.00Oct 6, 2026
- 100.00Oct 6, 2026
GPT-5.2 Pro: common questions
Who makes GPT-5.2 Pro?
GPT-5.2 Pro is made by OpenAI.
When was GPT-5.2 Pro released?
GPT-5.2 Pro was released on Dec 11, 2025, according to OpenAI's own announcement.
What is GPT-5.2 Pro good at?
GPT-5.2 Pro is behind the leaders in reasoning and math. Too few results yet to rate coding, agentic tasks, safety, long context, multimodal tasks, multilingual tasks, instruction following, or factuality.
How much does GPT-5.2 Pro cost?
GPT-5.2 Pro costs $21.00 per million input tokens and $168.00 per million output tokens, according to openai. At a mix of three input tokens to one output token, it costs more than 99% of the 328 priced models we track.
How many benchmarks has GPT-5.2 Pro been tested on?
We track 15 results for GPT-5.2 Pro on 11 benchmarks from 6 sources, 9 of them independently verified. The latest was recorded on Oct 6, 2026.
Which API features does GPT-5.2 Pro support?
OpenRouter lists tool calling, structured outputs, and reasoning for GPT-5.2 Pro.
About this record
Where GPT-5.2 Pro's numbers come from, and every name it appears under.
- Tracked since
- Apr 27, 2026
- Newest source mention
- May 20, 2026
Where the results come from
Verification: 15 scores · 9 independently verified · 6 vendor-reported. How these tiers are assigned
From 6 sources on 4 sites. api.llm-stats.com supplies 6 of them; the 9 independently verified results come from 3 sites. Bars are coloured by trust tier.
- api.llm-stats.com6
- arcprize.org5
- epoch.ai3
- simple-bench.com1
Also known as
How our sources name GPT-5.2 Pro at each reasoning setting.
| Setting | Short form |
|---|---|
| medium | gpt-5.2 pro (medium) |
| high | gpt-5.2 pro (high) |
| xhigh | gpt-5.2 pro (xhigh) |