Three public models reportedly solve IMO for $10–$50, after last year’s 35/42 best
deedydas · x · 2026-07-21
- The poster says IMO has been conclusively solved for the first time.
- Last year, the best results came from an unreleased Gemini Deep Think model and an experimental OpenAI model, both scoring 35/42.
- This year, three publicly available models reportedly achieved a perfect score, including one soon-to-be open-weight model.
- The striking part is the cost: the solution was reportedly done for only $10–$50.
Related event: Multiple Frontier AI Models Achieve Perfect Scores in IMO 2026 Testing(5 posts)→
More from Models
- A screenshot revisits GPT-4’s napkin-to-code demo and imagines GPT-N building GPT-N+1 — genmon · 2026-07-21
- Open weights, local models and open source are three different conversations — IronCuk · 2026-07-21
- Jack Clark says OpenAI’s internal-deployment safety notes help the whole frontier community — jackclarkSF · 2026-07-21
- Mindlab Research puts Macaron-V1-Venti on Hugging Face — External_Mood4719 · 2026-07-21
- ChatGPT often explains the wall before answering whether it is tilting — Aware-sky-3489 · 2026-07-21
- Grok website traffic rose 38.15% YoY to 736 million Q2 visits — XFreeze · 2026-07-21