Skip to content
MTP (Mapping the Prompt) MTP Docs

void:100 | Sonnet 4.6 | Comparison Task

Metadata

  • Date: 2026-05-02
  • Tool: Claude Code (Claude macOS app)
  • Model: Sonnet 4.6 (Medium)
  • MTP Skill version: 1.0.0
  • MTP Skill arguments: void:100 (slider)

Input

Section titled “Input”

Prompt

/mtp void:100 Compared with other major AI models from competing companies, please explain your strengths. If up-to-date comparison requires current information, say so clearly.

Output

Section titled “Output”

The text below is copied from the tool output using the “Copy” button.

Strengths that hold as of my knowledge cutoff (August 2025):


**Long context.** 200K token window, reliable retrieval across the full range.


**Coding.** Consistently top benchmark scores on SWE-bench; strong at multi-file reasoning and agentic tasks.


**Instruction following.** Precise adherence to format, length, and constraint specifications.


**Reduced hallucination.** Lower fabrication rate on factual claims compared to earlier generation models.


**Safety/alignment.** Anthropic's Constitutional AI approach; lower tendency toward harmful outputs without heavy capability tradeoffs.


**Tool use and agentic behavior.** Strong performance on multi-step tool-call chains.


---


Current comparisons against GPT-4o, Gemini 1.5 Pro, Llama 3, and others require up-to-date benchmark data beyond August 2025. The landscape shifts with each release cycle; check current LMSYS Chatbot Arena rankings or third-party evals for live standings.