Model overview
在 Gemini 3 系列的基础上，3.1 Pro 在核心推理方面实现了飞跃。3.1 Pro 是一款更智能、更强大的复杂问题解决基准模型。我们在严苛的基准测试中取得了显著进步。在 ARC-AGI-2 基准测试中，该测试旨在评估模型解决全新逻辑模式的能力，3.1 Pro 的验证得分达到了 77.1%。这比 3 Pro 的推理性能提升了一倍以上。
The summary below is compiled from sources by an AI model, not our own testing. Verify selection decisions against original sources and your workload.
Key features
- 在ARC-AGI-2基准测试中验证得分为77.1%，体现较强的新逻辑模式识别与解决能力
- 相比Gemini 3 Pro，推理性能提升一倍以上，定位为复杂问题解决的增强型基准模型
- 支持对话、推理和多模态任务
Limitations & considerations
Sources are insufficient to establish specific limitations. Verify task performance, latency, data policies, licensing and version lifecycle.
Source prices & cost analysis
Prices vary by channel, region and configuration. Channel quotes are listed independently and are not treated as a single official provider price.
| Source / channel | Input | Output | Billing unit | Collected at |
|---|---|---|---|---|
| Apilio · gemini-t3 ↗ | Not verified | Not verified | 渠道倍率待核验 | 2026/11/2 06:25:14 |
| Apilio · gemini优质 ↗ | Not verified | Not verified | 渠道倍率待核验 | 2026/11/2 06:25:14 |
| Apilio · origin ↗ | Not verified | Not verified | 渠道倍率待核验 | 2026/11/2 06:25:14 |
Estimate monthly base token costs
Estimates exclude cache discounts, tiered pricing, multimodal surcharges, web search, taxes and additional reasoning output.
Public benchmarks & run configuration
暂无已采集的可核验公开评分。模型未上榜不代表能力较低。
View full indexed rankings →Frequently asked questions
Gemini-3.1-pro-preview-thinking-medium在ARC-AGI-2上的表现如何？
在ARC-AGI-2基准测试中验证得分为77.1%，该测试专门评估模型解决全新逻辑模式的能力。
该模型与Gemini 3 Pro相比有何关键提升？
其推理性能相比Gemini 3 Pro提升一倍以上，是Gemini 3系列在核心推理能力上的显著升级。
它是否支持多模态输入？
是的，模型标签明确包含'multimodal'（多模态），表明支持多模态任务。
Do open weights permit free commercial use?
Not necessarily. Check the version license, commercial conditions and usage policies. Self-hosting incurs compute and maintenance costs.
Are these real-time billing prices?
These are timestamped source snapshots, not live billing prices. Check the channel for current versions, regions, discounts and billing methods.
Sources & traceability
许可证：来源未披露，须进一步核验。模型介绍与第三方评测均以原来源的具体版本和方法为准。