OpenAI, proprietary
GPT-5.2 Pro
GPT-5.2 Pro by OpenAI ranks 39th of 354 ranked models on the Noometry Index as of October 2026, with a score of 52.3. Its strongest category is math, where it ranks 29th. API pricing starts at $21 per million input tokens and $168 per million output tokens, with a 400K-token context window.
Last verified
Specifications
- Noometry rank
- #39 of 354
- Index score
- 52.3
- Evidence
- Reported 8 results
- Provider
- OpenAI
- Released
- December 11, 2025
- Weights
- Proprietary
- Reasoning
- Yes
- Context window
- 400K
- Max output
- 128K
- Input price
- $21 / M
- Output price
- $168 / M
- Blended price
- $57.75 / M
- Output speed
- Not measured
- Value
- #216 of 219
- Knowledge cutoff
- August 2025
- Input
- text, image
Category scores
Each category score combines every public result we have in that category.
- Reasoning 51.5
- Math 65.3
Strengths and weaknesses
Categories where GPT-5.2 Pro places highest and lowest among the models ranked in each, with its score against that category's median.
Closest competitors
The models ranked just above and below GPT-5.2 Pro. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| DeepSeek V4 Flash | #35 | 53.6 | $0.26 | 6 | Compare |
| GPT-6 Luna | #36 | 53.3 | $0.20 | — | Compare |
| Grok 4.7 | #37 | 53.1 | $3 | — | Compare |
| DeepSeek V4.1 Flash | #38 | 52.8 | $0.26 | — | Compare |
| Gemini 3 Flash Preview | #40 | 52.3 | $1.13 | — | Compare |
| GLM-5.3-Flash | #41 | 51.8 | $0.24 | — | Compare |
| Qwen3.7 Max | #42 | 51.5 | $3.75 | — | Compare |
| Qwen3.6 Max Preview | #43 | 51.5 | $2.92 | — | Compare |
Sponsored placements are available on pages like this one. Advertise on Noometry
Benchmark results
Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| ARC-AGI-2 | 54.2% | #32 of 83, top 39% | high | Epoch AI | |
| ARC-AGI-2 | 38.5% | medium | Epoch AI | ||
| SimpleBench | 57.4% | #30 of 77, top 39% | Epoch AI | ||
| NYT Connections (extended) | 79.3% | #37 of 91, top 41% | Lech Mazur benchmarks | ||
| ARC-AGI-1 | 85.7% | high | Epoch AI | ||
| ARC-AGI-1 | 81.2% | medium | Epoch AI | ||
| ARC-AGI-1 | 90.5% | #26 of 83, top 32% | xhigh | Epoch AI | |
| Epoch Capabilities Index | 155.4 | #28 of 213, top 14% | Epoch AI | 2025-12-11 |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| FrontierMath (Tiers 1-3) | 74% | #21 of 81, top 26% | xhigh | Epoch AI | 2026-06-13 |
| FrontierMath Tier 4 | 46% | #22 of 63, top 35% | xhigh | Epoch AI | 2026-06-13 |
| FrontierMath Tier 4 (v1) | 31.3% | #5 of 55, top 10% | Epoch AI | 2025-12-24 |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| openai | $21 | $168 | — | 2026-10-10 |
| openrouter | $21 | $168 | — | 2026-10-10 |
Compare GPT-5.2 Pro
- GPT-5.2 Pro vs GPT-5 Pro
- GPT-5.2 Pro vs DeepSeek V4.1 Flash
- GPT-5.2 Pro vs Gemini 3 Flash Preview
- GPT-5.2 Pro vs Grok 4.7
- GPT-5.2 Pro vs GLM-5.3-Flash
- GPT-5.2 Pro vs GPT-6 Luna
- GPT-5.2 Pro vs Qwen3.7 Max
- GPT-5.2 Pro vs Claude Fable 5.1
- GPT-5.2 Pro vs Gemini 3.8 Flash
- GPT-5.2 Pro vs Kimi K3
- GPT-5.2 Pro vs Grok 4.6
- GPT-5.2 Pro vs Qwen3.8 Max
- GPT-5.2 Pro vs GLM-5.3
- GPT-5.2 Pro vs Muse Spark 1.3
Other OpenAI models
- GPT-6 Astra70.8
- GPT-6.1 Sol65.6
- GPT-5.6 Sol65.0
- GPT-5.5 Pro64.3
- GPT-5.563.4
- GPT-6 Sol61.8
- GPT-5.459.4
- GPT-5.6 Terra59.2
Frequently asked questions
How good is GPT-5.2 Pro?
GPT-5.2 Pro by OpenAI ranks 39th of 354 ranked models on the Noometry Index as of October 2026, with a score of 52.3. Its strongest category is math, where it ranks 29th. API pricing starts at $21 per million input tokens and $168 per million output tokens, with a 400K-token context window.
How much does GPT-5.2 Pro cost?
GPT-5.2 Pro costs $21 per million input tokens and $168 per million output tokens on OpenAI's own API.
What is GPT-5.2 Pro's context window?
GPT-5.2 Pro accepts up to 400K tokens of input and can write up to 128K tokens in one response.
Is GPT-5.2 Pro open source?
No. GPT-5.2 Pro is proprietary and available only through OpenAI's API and partner platforms.
What are GPT-5.2 Pro's strengths and weaknesses?
Relative to other ranked models, GPT-5.2 Pro places best in math and lowest in reasoning.
What is GPT-5.2 Pro best at?
Its best category is math, where it ranks 29th on Noometry.