Version 5.6 Boosts Math Skills But Answers Remain Confusing
littmath · x · 2026-07-14
The author notes that 5.6 Sol Pro/Ultra shows significant math improvements over 5.5.
However, they complain about the actual UX: the model might "think" for over 100 minutes before delivering a baffling answer. Asking for an explanation triggers another 20 minutes of thinking, only to output even more confusing content.
Related event: New Model Boosts Math Power but Users Complain About Unreadable Output(2 posts)→
More from Models
- Nanbeige4.3-33B benchmarked: 59 tok/s single stream, ~1,060 tok/s across 64 concurrent runs — MaziyarPanahi · 2026-10-26
- Only 2 of 25 full ChatGPT rewrites flagged 100% AI by detectors — paulnovosad · 2026-10-26
- Qwen 4 Reportedly Spotted in the Arena, Hints at Alibaba's Next-Gen Model Testing — AIFlow_ML · 2026-10-26
- Nathan Lambert's first open models lecture: distillation, risks and the ecosystem explained — natolambert · 2026-10-26
- Nanbeige 4.3-33B flops real-world test: zero compilable output vs Qwen — julianharris · 2026-10-26
- Claude's safety classifier blocks SS7 defense research, pushing a security dev to an abliterated GLM — l4rz · 2026-10-26