ModelBeat
Models/Qwen3.7-Plus
All models
A
qwen/qwen3.7-plus

Qwen3.7-Plus is Alibaba’s AI model, released Jun 2, 2026. It costs $0.32/M input and $1.28/M output tokens, and handles a 1M-token context window. Its strongest use case is agentic & tools, where it ranks in the 67th percentile of the models Model Beat tracks.

Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series.

Context
1M
Input
$0.32 / 1M
Output
$1.28 / 1M
Released
Jun 2, 2026
Modalities
textimagetext
Strongest atAgentic & Tools top 33%Reasoning & Knowledge top 35%Math top 38%

Benchmarks

Scores on standardized evaluations. Higher is better — and rank shows where Qwen3.7-Plus lands among all models tracked on Model Beat.

63.0
Intelligence Index
Epoch AI
63rd percentile of tracked models
57.0
Coding Index
Epoch AI
57th percentile of tracked models
67.0
Agentic Index
Epoch AI
67th percentile of tracked models

Reasoning

2 evals
GPQA Diamond87.9%

Graduate-level scientific reasoning

Humanity's Last Exam35.6%

Frontier of human expert knowledge

Coding

1 evals
SciCode45.5%

Scientific research coding

Math

1 evals
AIME 2024/202593.3%

Olympiad-qualifier math

Agentic & Tools

1 evals
τ²-bench93.0%

Tool-agent-user reliability

In the news

3

Changelog

2
  • Qwen3.7-Plus: Humanity's Last Exam improved from 33.4% to 35.6% (+7%)benchmark · Aug 6, 2026
  • Qwen3.7 Plus (Qwen) added to the tracker.tracked · Jul 1, 2026

Compare Qwen3.7-Plus with

Frequently asked questions

What is Qwen3.7-Plus?

Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series.

Who created Qwen3.7-Plus?

Qwen3.7-Plus is an AI model developed by Alibaba, part of the Qwen family, released Jun 2, 2026.

How much does Qwen3.7-Plus cost?

Qwen3.7-Plus's list price from Alibaba is $0.32 per million input tokens and $1.28 per million output tokens.

What is Qwen3.7-Plus's context window?

Qwen3.7-Plus supports a context window of up to 1M tokens.

How does Qwen3.7-Plus perform on benchmarks?

On standardized evaluations tracked by Epoch AI, Qwen3.7-Plus scores 35.6% on Humanity's Last Exam, 93.0% on τ²-bench, 93.3% on AIME 2024/2025.

Benchmark data from Epoch AI (CC BY) and Artificial Analysis; pricing, specs & descriptions from OpenRouter. Data updated Aug 20, 2026.