GPT-5.2 Reasoning: pricing, context window and benchmarks
GPT-5.2 Reasoning is a frontier model from OpenAI. It offers a 1,000,000-token context window, costs $20.98 per million input tokens and $102.78 per million output tokens, and averages 87.5 across the index's benchmark suite.
Pricing
GPT-5.2 Reasoning costs $20.98 per million input tokens and $102.78 per million output tokens. A blended 3:1 input-to-output mix works out to about $41.43 per million tokens. Cached input is listed at $2.79 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $20.98 | per 1M tokens |
| Output | $102.78 | per 1M tokens |
| Cached input | $2.79 | per 1M tokens |
| Blended 3:1 | $41.43 | estimate per 1M tokens |
| 1M in + 1M out | $123.76 | estimate |
Benchmarks
Scores below are modelled estimates on a 0–100 scale. Use them to compare relative position, not as official vendor results.
| Benchmark | Score | Rank | Percentile | Relative |
|---|---|---|---|---|
| MMLU-Pro | 87.0 | 34 | 94th | |
| GPQA Diamond | 87.0 | 1 | 100th | |
| SWE-bench Verified | 78.2 | 15 | 98th | |
| HumanEval | 92.4 | 17 | 97th | |
| MATH-500 | 91.4 | 34 | 94th | |
| AIME 2025 | 84.9 | 41 | 93th | |
| LiveCodeBench | 84.6 | 8 | 99th | |
| IFEval | 95.0 | 5 | 99th | |
| TruthfulQA | 88.2 | 19 | 97th | |
| HellaSwag | 92.5 | 32 | 95th | |
| MMMU | 81.5 | 39 | 94th | |
| Arena Elo | 1500.4 | 2 | 100th |
What GPT-5.2 Reasoning is good for
GPT-5.2 Reasoning sits in the frontier tier of the index. It is aimed at work where answer quality matters more than unit cost: hard reasoning, multi-step coding, document analysis and multimodal inputs. At $20.98 per million input tokens and a 1,000,000-token context window, it is a premium option, so reserve it for tasks where a cheaper model measurably fails.
Strengths
- Top-tier average benchmark score (87.5), placing it #14 of 600.
- Large 1,000,000-token context window for long documents and agent traces.
- Accepts more than text, including image input where the provider supports it.
- Reasoning-oriented profile, useful for multi-step problems and structured analysis.
- Coding benchmarks are a relative strength within its tier.
Trade-offs
- Proprietary licence: you cannot download the weights or self-host the model.
- Premium input pricing at $20.98 per million tokens.
- Cost can climb quickly on long outputs and high-volume traffic.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Claude Opus 4.5 | Anthropic | 400000 | $19.42 | 87.7 |
| GPT-5.2 Reasoning | OpenAI | 1000000 | $20.98 | 87.5 |
| Gemini 3 Pro Reasoning | Google DeepMind | 200000 | $19.69 | 87.5 |
| o4 Reasoning | OpenAI | 1000000 | $19.69 | 87.5 |
| GPT-5.2 Turbo | OpenAI | 1000000 | $20.73 | 87.4 |
| GPT-5.2 Vision | OpenAI | 1000000 | $19.03 | 87.4 |
FAQ
How much does GPT-5.2 Reasoning cost?
GPT-5.2 Reasoning is listed at $20.98 per million input tokens and $102.78 per million output tokens. Cached input is $2.79 per million tokens. A blended 3:1 input-to-output mix is about $41.43 per million tokens.
What is the context window of GPT-5.2 Reasoning?
GPT-5.2 Reasoning has a context window of 1,000,000 tokens and can emit up to 65,536 output tokens per request in this index.
Is GPT-5.2 Reasoning open weights?
No. GPT-5.2 Reasoning is a proprietary model with a proprietary licence, so you cannot download the weights.
How does GPT-5.2 Reasoning score on benchmarks?
GPT-5.2 Reasoning averages 87.5 across the scored benchmarks in this index, ranking #14 of 600 models. Its strongest relative result is GPQA Diamond at 87.0.
What is GPT-5.2 Reasoning best for?
GPT-5.2 Reasoning sits in the frontier tier of the index. It is aimed at work where answer quality matters more than unit cost: hard reasoning, multi-step coding, document analysis and multimodal inputs. At $20.98 per million input tokens and a 1,000,000-token context window, it is a premium option, so reserve it for tasks where a cheaper model measurably fails.