What a 20x20-digit multiplication actually looks like by hand, per one LLM eval author
maksym_andr · x · 2026-09-17
maksymandr shared a photo of a full 20x20-digit long multiplication, showing the roughly twenty rows of partial products that make hand calculation nearly error-prone.
Context from his eval: GPT-6-Astra can't run without CoT and scores 99.6% at the lowest effort setting, while Claude Opus 5 gets 1200/1200 correct at max reasoning.
Related event: Claude Opus 5 Aces 20×20-Digit Multiplication, 1200/1200 Without Tools(7 posts)→
More from Models
- Mystery model 'Union Alpha' tops DeepSWE, claiming GPT-6-class capability at DeepSeek-level prices — daniel_mac8 · 2026-09-17
- Jensen Huang at All-In Summit: AI leadership will be built by everyone, open and closed models both matter — NVIDIAAI · 2026-09-17
- Model 'Jev' shows well-calibrated probabilities: 1.74pp average calibration error across benchmarks — hackgoofer · 2026-09-17
- Filtering synthetic envs where Qwen deterministically fails but GLM5.3 solves reveals odd behaviors — kalomaze · 2026-09-17
- Why keep a no-thinking mode in 2026? CoT monitoring and performance both demand reasoning — scaling01 · 2026-09-17
- Dev builds sourced comparison of realtime speech-to-speech models across six providers — mahimairaja · 2026-09-17