voidful/Qwen3.5-9B-gemini-3.1-opus-4.6-reasoning

VISIONPricing:Input $0.431 / Cached $0.0862 / Output $1.12Concurrent Unit Cost:1Model Size:9BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Mar 7, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

The voidful/Qwen3.5-9B-gemini-3.1-opus-4.6-reasoning is a 9 billion parameter causal language model based on Qwen/Qwen3.5-9B, with a 32768 token context length. It is specifically fine-tuned to enhance reasoning-oriented multiple-choice performance, demonstrating improved scores on benchmarks like ARC-Challenge, ARC-Easy, and BoolQ. This model excels in structured reasoning and calibrated answer selection, making it suitable for tasks requiring strong analytical capabilities.

Loading preview...

Model Overview

voidful/Qwen3.5-9B-gemini-3.1-opus-4.6-reasoning is a 9 billion parameter causal language model built upon the Qwen/Qwen3.5-9B architecture. Its primary focus is to significantly improve performance on reasoning-oriented multiple-choice tasks while maintaining robust general capabilities. The model was fine-tuned using the voidful/gemini-3.1-opus-4.6-reasoning-merged dataset.

Key Capabilities & Performance

  • Enhanced Reasoning: Demonstrates notable improvements in structured reasoning and calibrated answer selection.
  • Benchmark Leadership: Achieves the best overall aggregate performance in zero-shot evaluations against Qwen/Qwen3.5-9B and DavidAU/Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT.
  • Specific Strengths: Shows significant gains on ARC-Challenge, ARC-Easy, and BoolQ benchmarks, indicating strong performance in science and reading-style reasoning tasks.
  • Competitive General Capability: Maintains competitive performance on other zero-shot commonsense tasks, though it may be slightly behind some baselines on HellaSwag and OpenBookQA.

Ideal Use Cases

This model is particularly well-suited for applications requiring:

  • Reasoning-oriented zero-shot performance: Excels in scenarios where logical deduction and precise answer selection are critical.
  • Multiple-choice question answering: Optimized for tasks involving structured reasoning and selecting the best option from a set.
  • Analytical tasks: Benefits use cases that demand strong analytical capabilities and calibrated responses.

Finetunes
1 models