Claude Opus 5 is claimed to score 42/42 on IMO 2026 without tools or an agent harness
davidwromero · x · 2026-07-26
A repost claims Claude Opus 5 solved the IMO 2026 problems at gold-medal level and shares the raw reasoning trace.
- The poster says 6 solutions appear correct when judged by GPT-5.6.
- The run reportedly used no agent harness or tools.
- For one problem, the model hit the 128k output limit and a second request was sent.
- The original quote claims a perfect 42/42 score, making this a notable model-capability signal.
Related event: Rumor Claims Claude Opus 5 Achieves Perfect 2026 IMO Score Without Tools(5 posts)→
More from Models
- MissionReport benchmark: only 3 of 540 AI-generated government reports pass all criteria — Exp_Mark · 2026-10-27
- Local beats cloud: Qwen 3.8 FN handles private student data as well as frontier models — dr_lm · 2026-10-27
- Aidan Gomez: model's CoT said no tool calls right before making them — aidangomez · 2026-10-27
- Nat Lambert: Cohere's model is narrow RL training on internal infra ill-suited for open weights — natolambert · 2026-10-27
- OpenAI teases DOTS is coming to Europe 'soon' — mark_k · 2026-10-27
- Clifford Pickover challenges AI to decipher a message he encoded in Norse runes — pickover · 2026-10-27