GregKamradt crowdsources hardest one-shot questions to test ~50 models
GregKamradt · x · 2026-09-11
GregKamradt is crowdsourcing the hardest one-shot questions for AI, aiming to run 50 models through a curated list to see which ones actually hold up. He has shared his current question list and invites contributions.
Related event: GregKamradt Seeks Hardest One-Shot Questions to Benchmark ~50 Models(2 posts)→
More from Models
- Users notice o5 constantly self-measures while f5/5.1 barely does — repligate · 2026-09-11
- Chinese labs' distillation scale revealed: Alibaba 151M+ exchanges, Moonshot 23M+, DeepSeek 12.1M+ — scaling01 · 2026-09-11
- Astra usage limits worse than Fable: burn a week's quota in a single day — cocktailpeanut · 2026-09-11
- DeepSeek V4.1 Flash Architecture: 552B MoE with Asymmetric 8B Read / 16B Decode Compute — demian_ai · 2026-09-11
- Insider: chances are zero that opt-in Codex data made it into OpenAI training runs — soumitrashukla9 · 2026-09-11
- FrontierMath Tier 4 fully solved: GPT-6 Astra cracks the last problem standing — Jsevillamol · 2026-09-11