Gemini 3.1 Pro PreviewvsClaude Opus 4.6
在 15 个共同 benchmark 中，Gemini 3.1 Pro Preview 整体领先：Gemini 3.1 Pro Preview 领先 8 项，Claude Opus 4.6 领先 6 项，持平 1 项，平均分差 +1.71。
Gemini 3.1 Pro Preview
Google Deep Mind · 2026-02-20 · 多模态大模型
Claude Opus 4.6
Anthropic · 2026-02-05 · 推理大模型
Gemini 3.1 Pro Preview8 项(53%)持平1(40%)6 项Claude Opus 4.6
评测分数
按能力类目分组，每组内按分差大小排列；共 15 项。
General Knowledge
Gemini 3.1 Pro Preview 领先 3/5| 评测项 | Gemini 3.1 Pro Preview | Claude Opus 4.6 | 分差 |
|---|---|---|---|
| ARC-AGI-2 | 77.107 / 59Thinking High (No Tools) | 66.3015 / 59Extended (no tools) | +10.80 |
| GPQA Diamond | 94.303 / 178Thinking High (No Tools) | 91.3114 / 178Extended (no tools) | +2.99 |
| HLE | 51.4015 / 157Thinking High (With Tools) | 5311 / 157Extended (with tools, internet) | -1.60 |
| MMLU | 92.603 / 65Thinking High (No Tools) | 91.057 / 65Extended (no tools) | +1.55 |
| ARC-AGI-3 | 03 / 6Thinking High (No Tools) | 01 / 6最高（无工具） | 持平 |
Agent Level Benchmark
胶着 2/2| 评测项 | Gemini 3.1 Pro Preview | Claude Opus 4.6 | 分差 |
|---|---|---|---|
| τ²-Bench | 90.802 / 40Thinking High (With Tools) | 91.891 / 40Extended (with tools) | -1.09 |
| τ²-Bench - Telecom | 99.301 / 35Thinking High (With Tools) | 99.252 / 35Extended (with tools) | +0.05 |
Coding and Software Engineer
胶着 2/2| 评测项 | Gemini 3.1 Pro Preview | Claude Opus 4.6 | 分差 |
|---|---|---|---|
| LiveCodeBench | 91.703 / 120Thinking High (With Tools) | 7637 / 120Extended (no tools) | +15.70 |
| SWE-bench Verified | 80.6010 / 108Thinking High (With Tools) | 80.849 / 108Extended (with tools) | -0.24 |
Math and Reasoning
Claude Opus 4.6 领先 2/2| 评测项 | Gemini 3.1 Pro Preview | Claude Opus 4.6 | 分差 |
|---|---|---|---|
| FrontierMath - Tier 4 | 16.7020 / 80Normal (No Tools) | 22.9012 / 80最高（无工具） | -6.20 |
| FrontierMath | 36.9011 / 60Thinking High (No Tools) | 40.707 / 60最高（无工具） | -3.80 |
AI Agent - Information Search
Gemini 3.1 Pro Preview 领先 1/1| 评测项 | Gemini 3.1 Pro Preview | Claude Opus 4.6 | 分差 |
|---|---|---|---|
| BrowseComp | 85.903 / 45Thinking High (With Tools + Internet) | 847 / 45Thinking (With Tools + Internet) | +1.90 |
AI Agent - Tool Usage
Gemini 3.1 Pro Preview 领先 1/1| 评测项 | Gemini 3.1 Pro Preview | Claude Opus 4.6 | 分差 |
|---|---|---|---|
| Terminal Bench 2.0 | 68.508 / 46Thinking High (With Tools) | 65.4011 / 46Extended (with tools) | +3.10 |
Claw-style Agent Evaluation
Claude Opus 4.6 领先 1/1| 评测项 | Gemini 3.1 Pro Preview | Claude Opus 4.6 | 分差 |
|---|---|---|---|
| Pinch Bench | 86.7010 / 37Thinking (With Tools) | 87.407 / 37Thinking (With Tools) | -0.70 |
Multimodal Understanding
Gemini 3.1 Pro Preview 领先 1/1| 评测项 | Gemini 3.1 Pro Preview | Claude Opus 4.6 | 分差 |
|---|---|---|---|
| MMMU | 80.5011 / 28Thinking High (No Tools) | 77.3015 / 28Extended (with tools) | +3.20 |
规格对比
| 字段 | Gemini 3.1 Pro Preview | Claude Opus 4.6 |
|---|---|---|
| 发布机构 | Google Deep Mind | Anthropic |
| 发布时间 | 2026-02-20 | 2026-02-05 |
| 模型类型 | 多模态大模型 | 推理大模型 |
| 架构 | 稠密模型 | 稠密模型 |
| 参数规模 | 暂无数据 | 暂无数据 |
| 上下文长度 | 1M | 1000K |
| 最大输出 | 32K | 64K |
API 调用价格
价格优先使用 DataLearner 配置的 API 记录；缺失项不做推测。
| 价格项 | Gemini 3.1 Pro Preview | Claude Opus 4.6 |
|---|---|---|
| 文本输入 | $2 / 1M tokens | $0.5 / 1M tokens |
| 文本输出 | $12 / 1M tokens | $25 / 1M tokens |
| 缓存读取 | 暂无公开价格 | $0.5 / 1M tokens |
| 缓存写入 | 暂无公开价格 | $10 / 1M tokens |
小结
- Gemini 3.1 Pro Preview在以下类目领先:General Knowledge (3/5)、AI Agent - Information Search (1/1)、AI Agent - Tool Usage (1/1)、Multimodal Understanding (1/1)
- Claude Opus 4.6在以下类目领先:Math and Reasoning (2/2)、Claw-style Agent Evaluation (1/1)
- 胶着类目:Agent Level Benchmark、Coding and Software Engineer
15 个共同 benchmark 上，Gemini 3.1 Pro Preview 平均高出 1.71 分。
单项差距最大的 benchmark：LiveCodeBench — Gemini 3.1 Pro Preview 91.70，Claude Opus 4.6 76（分差 +15.70）。
本页正文由结构化模型、价格与 benchmark 数据生成，不使用实时 LLM 撰写。