Claude Sonnet 4.5vsQwen3-Coder-Next
Claude Sonnet 4.5 | Qwen3-Coder-Next | |
|---|---|---|
| Specifications | ||
Parameters | — | 80B |
Context window | — | 256k |
| Benchmarks | ||
Nonsense detection BullshitBench v2Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | 79% | — |
Agentic coding SWE-Bench ProCan the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better. | — | 44.3% |
Coding SWE-Bench VerifiedReal coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 77.2%Best | 70.6% |
Multilingual coding SWE-Bench MultilingualLike SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | — | 62.8% |
Next.js coding Next.js EvalsVercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better. | 50% | — |
Agentic terminal coding Terminal-Bench 2.0Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. | — | 36.2% |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 83.4% | — |
Multimodal MMMUTests the AI on understanding images and text together across many college subjects. Higher is better. | 68% | — |
| Overview | ||
| Company | Anthropic | Qwen |
| Release date | Sep 29 2025 | Feb 3 2026 |
| Access | Proprietary | Open Weight |
Which is better: Claude Sonnet 4.5 or Qwen3-Coder-Next?
Claude Sonnet 4.5 leads Qwen3-Coder-Next on 1 of the 1 benchmark they both report (SWE-Bench Verified). Claude Sonnet 4.5 shipped 127 days before Qwen3-Coder-Next, so benchmark comparisons should account for the intervening progress.
Claude Sonnet 4.5 is proprietary, while Qwen3-Coder-Next is open weight.
On SWE-Bench Verified, Claude Sonnet 4.5 leads at 77.2% vs Qwen3-Coder-Next at 70.6%.
Frequently asked questions
Claude Sonnet 4.5 was released by Anthropic on Sep 29 2025.
Qwen3-Coder-Next was released by Qwen on Feb 3 2026.
Claude Sonnet 4.5 leads on SWE-Bench Verified — Claude Sonnet 4.5 77.2% vs Qwen3-Coder-Next 70.6%.
Claude Sonnet 4.5 is a proprietary model released by Anthropic. Qwen3-Coder-Next is an open weight model released by Qwen.
Other comparisons
Claude Sonnet 4.5vsGPT-5.6 SolQwen3-Coder-NextvsGPT-5.6 SolClaude Sonnet 4.5vsGemini 3.6 FlashQwen3-Coder-NextvsGemini 3.6 FlashClaude Sonnet 4.5vsMuse Spark 1.1Qwen3-Coder-NextvsMuse Spark 1.1Claude Sonnet 4.5vsGrok 4.5Qwen3-Coder-NextvsGrok 4.5Claude Sonnet 4.5vsDeepSeek-V4-Flash-0731Qwen3-Coder-NextvsDeepSeek-V4-Flash-0731Claude Sonnet 4.5vsMistral Medium 3.5Qwen3-Coder-NextvsMistral Medium 3.5