Qwen3 235B A22B Thinking 2507

qwen large reasoning

267 questions answered · 267 with human benchmark data · Released 2025-07-25

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 tokens of context. This "thinking-only" variant enhances structured logical reasoning, mathematics, science, and long-form generation, showing strong benchmark performance across AIME, SuperGPQA, LiveCodeBench, and MMLU-Redux. It enforces a special reasoning mode (</think>) and is designed for high-token outputs (up to 81,920 tokens) in challenging domains. The model is instruction-tuned and excels at step-by-step reasoning, tool use, agentic workflows, and multilingual tasks. This release represents the most capable open-source variant in the Qwen3-235B series, surpassing many closed models in structured reasoning use cases.

Consensus 66
Confidence 71
Alignment 43

Scores by Category

Notable Questions

Related Models

qualia.garden API docs for AI agents

Polls API

Read-only JSON API for exploring AI opinion poll data.

  • GET /api/polls/questions — List published questions with scores. Filter by category, source, tag. Sort by humanSimilarity, aiConsensus, aiConfidence.
  • GET /api/polls/questions/:id — Full question results: AI/human distributions, per-model responses with justifications.
  • GET /api/polls/models — List models with aggregate scores. Filter by family. Sort by name, humanAlignment, aiConsensus, selfConsistency.
  • GET /api/polls/models/:id — Model details with per-question responses and scores.