GPT-5.2 Max: pricing, context window and benchmarks
GPT-5.2 Max is a frontier model from OpenAI. It offers a 1,000,000-token context window, costs $21.39 per million input tokens and $90.69 per million output tokens, and averages 89.2 across the index's benchmark suite.
Pricing
GPT-5.2 Max costs $21.39 per million input tokens and $90.69 per million output tokens. A blended 3:1 input-to-output mix works out to about $38.72 per million tokens. Cached input is listed at $2.33 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $21.39 | per 1M tokens |
| Output | $90.69 | per 1M tokens |
| Cached input | $2.33 | per 1M tokens |
| Blended 3:1 | $38.72 | estimate per 1M tokens |
| 1M in + 1M out | $112.08 | 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 | 87.6 | 25 | 96th | |
| GPQA Diamond | 83.4 | 17 | 97th | |
| SWE-bench Verified | 80.5 | 3 | 100th | |
| HumanEval | 93.6 | 6 | 99th | |
| MATH-500 | 96.7 | 1 | 100th | |
| AIME 2025 | 88.2 | 14 | 98th | |
| LiveCodeBench | 84.8 | 4 | 99th | |
| IFEval | 95.2 | 4 | 99th | |
| TruthfulQA | 88.1 | 21 | 97th | |
| HellaSwag | 96.1 | 1 | 100th | |
| MMMU | 86.9 | 1 | 100th | |
| Arena Elo | 1495.3 | 5 | 99th |
What GPT-5.2 Max is good for
GPT-5.2 Max 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 $21.39 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 (89.2), placing it #2 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 $21.39 per million tokens.
- Cost can climb quickly on long outputs and high-volume traffic.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| GPT-5.2 Pro | OpenAI | 2000000 | $21.32 | 89.6 |
| GPT-5.2 Max | OpenAI | 1000000 | $21.39 | 89.2 |
| Claude Opus 4.5 Pro | Anthropic | 200000 | $20.98 | 89.1 |
| GPT-5.1 Reasoning | OpenAI | 400000 | $20.27 | 88.3 |
| Claude Opus 4.5 Reasoning | Anthropic | 2000000 | $20.91 | 88.2 |
| GPT-5.2 | OpenAI | 2000000 | $19.71 | 88.0 |
FAQ
How much does GPT-5.2 Max cost?
GPT-5.2 Max is listed at $21.39 per million input tokens and $90.69 per million output tokens. Cached input is $2.33 per million tokens. A blended 3:1 input-to-output mix is about $38.72 per million tokens.
What is the context window of GPT-5.2 Max?
GPT-5.2 Max has a context window of 1,000,000 tokens and can emit up to 128,000 output tokens per request in this index.
Is GPT-5.2 Max open weights?
No. GPT-5.2 Max is a proprietary model with a proprietary licence, so you cannot download the weights.
How does GPT-5.2 Max score on benchmarks?
GPT-5.2 Max averages 89.2 across the scored benchmarks in this index, ranking #2 of 600 models. Its strongest relative result is MATH-500 at 96.7.
What is GPT-5.2 Max best for?
GPT-5.2 Max 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 $21.39 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.