L Models Long context

Qwen3 235B A22B Thinking 2507

Name: Qwen3 235B A22B Thinking 2507
Author: Qwen

by Qwen

Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B paramet

Visit Qwen Submit your build →

Models

Qwen3 235B A22B Thinking 2507

Added 10 July 2026

#qwen

Overview

Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...

How to use / API access

Call via OpenRouter with model id `qwen/qwen3-235b-a22b-thinking-2507`.

openrouter · qwen/qwen3-235b-a22b-thinking-2507 Docs

OpenRouter id: qwen/qwen3-235b-a22b-thinking-2507

Benchmarks

Intelligence Index (artificial-analysis) : 19.6 index
Coding Index (artificial-analysis) : 22.1 index
Agentic Index (artificial-analysis) : 3.8 index
Design Arena 3d (other) : 1074 elo · #81
Design Arena codecategories (other) : 1076 elo · #85
Design Arena dataviz (other) : 989 elo · #92
Design Arena gamedev (other) : 1023 elo · #94

Notes

Qwen3 235B A22B Thinking 2507 is listed in the EDNA Models directory from the OpenRouter catalogue.

← Back to Models Submit your own entry →