Gemini 3 Pro Max: pricing, context window and benchmarks
Gemini 3 Pro Max is a frontier model from Google DeepMind. It offers a 2,000,000-token context window, costs $20.57 per million input tokens and $112.92 per million output tokens, and averages 87.9 across the index's benchmark suite.
Pricing
Gemini 3 Pro Max costs $20.57 per million input tokens and $112.92 per million output tokens. A blended 3:1 input-to-output mix works out to about $43.66 per million tokens. Cached input is listed at $2.31 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $20.57 | per 1M tokens |
| Output | $112.92 | per 1M tokens |
| Cached input | $2.31 | per 1M tokens |
| Blended 3:1 | $43.66 | estimate per 1M tokens |
| 1M in + 1M out | $133.49 | 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 | 89.5 | 10 | 98th | |
| GPQA Diamond | 81.8 | 33 | 95th | |
| SWE-bench Verified | 76.6 | 24 | 96th | |
| HumanEval | 91.9 | 24 | 96th | |
| MATH-500 | 92.1 | 19 | 97th | |
| AIME 2025 | 89.6 | 8 | 99th | |
| LiveCodeBench | 83.6 | 10 | 98th | |
| IFEval | 94.7 | 7 | 99th | |
| TruthfulQA | 89.6 | 6 | 99th | |
| HellaSwag | 92.6 | 31 | 95th | |
| MMMU | 84.4 | 11 | 98th | |
| Arena Elo | 1477.5 | 24 | 96th |
What Gemini 3 Pro Max is good for
Gemini 3 Pro 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 $20.57 per million input tokens and a 2,000,000-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 (87.9), placing it #8 of 600.
- Large 2,000,000-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 $20.57 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 | OpenAI | 2000000 | $19.71 | 88.0 |
| GPT-5.1 Max | OpenAI | 2000000 | $20.50 | 87.9 |
| Gemini 3 Pro Max | Google DeepMind | 2000000 | $20.57 | 87.9 |
| Claude Opus 4.5 Max | Anthropic | 1000000 | $20.90 | 87.8 |
| GPT-5.1 Pro | OpenAI | 200000 | $19.77 | 87.8 |
| Grok 4 Reasoning | xAI | 2000000 | $19.67 | 87.8 |
FAQ
How much does Gemini 3 Pro Max cost?
Gemini 3 Pro Max is listed at $20.57 per million input tokens and $112.92 per million output tokens. Cached input is $2.31 per million tokens. A blended 3:1 input-to-output mix is about $43.66 per million tokens.
What is the context window of Gemini 3 Pro Max?
Gemini 3 Pro Max has a context window of 2,000,000 tokens and can emit up to 128,000 output tokens per request in this index.
Is Gemini 3 Pro Max open weights?
No. Gemini 3 Pro Max is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Gemini 3 Pro Max score on benchmarks?
Gemini 3 Pro Max averages 87.9 across the scored benchmarks in this index, ranking #8 of 600 models. Its strongest relative result is IFEval at 94.7.
What is Gemini 3 Pro Max best for?
Gemini 3 Pro 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 $20.57 per million input tokens and a 2,000,000-token context window, it is a premium option, so reserve it for tasks where a cheaper model measurably fails.