Gemini 3 Pro Reasoning: pricing, context window and benchmarks
Gemini 3 Pro Reasoning is a frontier model from Google DeepMind. It offers a 200,000-token context window, costs $19.69 per million input tokens and $98.36 per million output tokens, and averages 87.5 across the index's benchmark suite.
Pricing
Gemini 3 Pro Reasoning costs $19.69 per million input tokens and $98.36 per million output tokens. A blended 3:1 input-to-output mix works out to about $39.36 per million tokens. Cached input is listed at $2.92 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $19.69 | per 1M tokens |
| Output | $98.36 | per 1M tokens |
| Cached input | $2.92 | per 1M tokens |
| Blended 3:1 | $39.36 | estimate per 1M tokens |
| 1M in + 1M out | $118.05 | 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 | 90.1 | 5 | 99th | |
| GPQA Diamond | 83.9 | 13 | 98th | |
| SWE-bench Verified | 76.3 | 27 | 96th | |
| HumanEval | 90.2 | 43 | 93th | |
| MATH-500 | 93.3 | 9 | 99th | |
| AIME 2025 | 88.8 | 12 | 98th | |
| LiveCodeBench | 82.0 | 25 | 96th | |
| IFEval | 93.8 | 13 | 98th | |
| TruthfulQA | 90.3 | 2 | 100th | |
| HellaSwag | 93.5 | 18 | 97th | |
| MMMU | 80.8 | 46 | 92th | |
| Arena Elo | 1485.0 | 16 | 97th |
What Gemini 3 Pro Reasoning is good for
Gemini 3 Pro 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 $19.69 per million input tokens and a 200,000-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 #15 of 600.
- Large 200,000-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 $19.69 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 Gemini 3 Pro Reasoning cost?
Gemini 3 Pro Reasoning is listed at $19.69 per million input tokens and $98.36 per million output tokens. Cached input is $2.92 per million tokens. A blended 3:1 input-to-output mix is about $39.36 per million tokens.
What is the context window of Gemini 3 Pro Reasoning?
Gemini 3 Pro Reasoning has a context window of 200,000 tokens and can emit up to 8,192 output tokens per request in this index.
Is Gemini 3 Pro Reasoning open weights?
No. Gemini 3 Pro Reasoning is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Gemini 3 Pro Reasoning score on benchmarks?
Gemini 3 Pro Reasoning averages 87.5 across the scored benchmarks in this index, ranking #15 of 600 models. Its strongest relative result is TruthfulQA at 90.3.
What is Gemini 3 Pro Reasoning best for?
Gemini 3 Pro 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 $19.69 per million input tokens and a 200,000-token context window, it is a premium option, so reserve it for tasks where a cheaper model measurably fails.