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

Llama 4 Maverick vs Qwen3.7 Plus

Meta meets Qwen: 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.

Meta 对 Qwen: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

Llama 4 Maverick   Qwen3.7 Plus · 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

Llama 4 MaverickQwen3.7 Plus
Provider厂商MetaQwen
Released发布2025-04-052026-06-03
Intelligence Score智能评分41.181.7
Benchmark coveragebenchmark 覆盖95%76%
Reasoning推理41.577.5
Coding代码39.686.9
Knowledge知识84.793.2
Math数学1185.7
Agent智能体1893.8
Preference偏好29.539.8
API input $/1M输入价 $/百万$0.200$0.320
API output $/1M输出价 $/百万$0.696$1.28
Blended $/1M混合价 $/百万$0.448$0.800
Value (score per $)性价比(分数/美元)91.7102.1
Context window上下文1M1M
Max output最大输出115K131K
Reasoning tiers推理档位thinking on / off
Open weights开放权重Yes支持Yes支持
CN-direct国内直连NoYes支持
Free tier免费层NoNo

Benchmark by benchmark逐项 benchmark

Benchmark基准Llama 4 MaverickQwen3.7 Plus
Humanity's Last Exam5.6834.7
GPQA Diamond69.890.3
MMLU-Pro80.588.5
AIME 20252085.7
LiveCodeBench43.489.6
Terminal-Bench8.870.3
τ²-bench17.893
LMArena (Chatbot Arena)14171458

Llama 4 Maverick dossier → 档案 → · Qwen3.7 Plus dossier → 档案 → · How we score评分方法