The AI tools index that doesn't waste your time.不浪费你时间的 AI 工具索引。
Head-to-head正面对比

Claude Opus 5 vs Gemini 3.1 Pro Preview

Anthropic meets Google: sourced benchmark scores side by side, dimension by dimension, with prices and specs. Every conclusion below is derived from the published dataset — no opinions, no sponsorship.

Anthropic 对 Google:带来源的 benchmark 成绩逐项并排,附价格与规格。下面每条结论都从公开数据集推导——没有主观意见,没有厂商赞助。

The verdict, derived from data结论(全部由数据推导)

ReaCodKnoMatAgtPre

Claude Opus 5   Gemini 3.1 Pro Preview · missing dimensions count as 0 in the chart缺数据的维度在图上按 0 计

Spec by spec逐项规格

Claude Opus 5Gemini 3.1 Pro Preview
Provider厂商AnthropicGoogle
Released发布2026-07-242026-02-19
Intelligence Score智能评分8882.4
Benchmark coveragebenchmark 覆盖100%100%
Reasoning推理96.490.5
Coding代码85.985.6
Knowledge知识96.494.5
Math数学68.158.5
Agent智能体78.685.7
Preference偏好10046.8
API input $/1M输入价 $/百万$5.00$2.00
API output $/1M输出价 $/百万$25$12
Blended $/1M混合价 $/百万$15$7.00
Value (score per $)性价比(分数/美元)5.911.8
Context window上下文1M1M
Max output最大输出128K66K
Reasoning tiers推理档位low / medium / high / x-highminimal / low / medium / high
Open weights开放权重NoNo
CN-direct国内直连NoNo
Free tier免费层NoNo

Benchmark by benchmark逐项 benchmark

Benchmark基准Claude Opus 5Gemini 3.1 Pro Preview
Humanity's Last Exam54.4⚡max46.44⚡high
GPQA Diamond93.795.5
MMLU-Pro91.5989.8
SWE-bench Verified9680.6
AIME 20259793.3
LiveCodeBench89.0391.7
FrontierMath31.2516.7
Terminal-Bench43.5⚡max68.5
τ²-bench82.7895.6
LMArena (Chatbot Arena)1699⚡max1486
WebArena6869

Claude Opus 5 dossier → 档案 → · Gemini 3.1 Pro Preview dossier → 档案 → · How we score评分方法