https://x.com/LuminaBench/status/2088283230495551590

🚨Qwen3.8 27B benchmarks are ridiculous

How is a 27B model even putting up numbers like this

• SWE bench Pro: 61.7 • QwenSWEBench: 79.0 • CoWorkBench: 70.7 • LiveCodeBench: 90.3

It’s genuinely Opus 4.6 level while being small enough to run on a desktop😭

27B models should not be this good, what the hell did Qwen do