1. Advanced Coding Performance

• Achieves 74.5% on SWE-bench Verified, improving the Claude family's state-of-the-art coding abilities.

• Stronger at:

  • Multi-file code refactoring
  • Large codebase debugging
  • Pinpointing exact corrections without unnecessary edits

• Outperforms Opus 4 and shows gains comparable to jumps seen in past major releases.

2. Improved Agentic & Research Capabilities

• Better at maintaining detail accuracy in long research tasks.
• Enhanced agentic search and step-by-step problem solving.
• Performs reliably across complex multi-turn reasoning tasks.

3. Validated by Real-World Users

• GitHub: Better multi-file refactoring and code adjustments.
• Rakuten Group: High precision debugging with minimal collateral changes.
• Windsurf: One standard deviation improvement on their junior dev benchmark - similar magnitude to Sonnet 3.7 → Sonnet 4.

4. Hybrid-Reasoning Benchmark Improvements

• Improvements across TAU-bench, GPQA Diamond, MMMLU, MMMU, AIME (with extended thinking).
• Stronger robustness in long-context reasoning tasks.

1. Strongest visual reasoning in Qwen lineup

• Handles charts, diagrams, puzzles.

2. Great for math + vision hybrids

• Geometry, visual logic testing.

3. High-quality instruction following

• Consistent formatting and detailed responses.