Qwen 3.7 Plus outperforms GPT-5.4 and Claude-Opus-4.6 across 12 reasoning tests on LisanBench

Positive users praise Qwen3.7-Plus for outperforming rivals like Opus in multimodal benchmarks and setting a high bar, while negative users dismiss the API release as pointless without open weights or source.

39 comments with sentiment. View comments.