๐จ OMG! Qwen just released Qwen3.6-27B! This is an update to the King ๐ of Open Source Med Models!
A 27B dense model that beats the much larger Qwen3.5-397B-A17B (~15x bigger) on coding benchmarks! ๐คฏ
Watch out Opus 4.7
Key wins:
โข SWE-Bench Verified: 77.2 (vs 76.2)
โข SWE-Bench Pro: 53.5 (vs 50.9)
โข Terminal-Bench 2.0: 59.3 (vs 52.5)
โ Strong multimodal reasoning
โ Thinking + Non-thinking modes
โ Apache 2.0 (fully open)
Smaller model. Flagship performance. ๐ฅ