Open-source open-weight model scores an IMO gold-medal result with 30/42
srchvrs · x · 2026-07-22
Open-source open-weight model gets an IMO gold-medal score
An open-source, open-weight Nemotron-based system scored 30/42 at the International Mathematical Olympiad 2026.
- The IMO team officially graded the solutions and certified the result as equivalent to a human gold medal.
- The post frames this as the first verified gold-medal achievement for an open-source open-weight model.
Related event: NVIDIA Nemotron Achieves Gold-Level Score at IMO 2026(3 posts)→
More from Models
- Benchmark scores drop from 89% to 19% on new evals — how benchmaxxing breaks leaderboard trust — airesearch12 · 2026-09-11
- Developer Building a Unified Leaderboard of All Model Benchmark Scores — airesearch12 · 2026-09-11
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11
- GPT-5.6 writes well but is instantly forgettable, user complains — BasedRaddka · 2026-09-11
- Opus Refuses Protein Research Codebase Over 'Safety' Concerns, Dev Considers Rolling His Own — josephdviviano · 2026-09-11
- User Hails Unconfirmed 'DeepSeek 4.1 Flash' as an Inflection Point in LLMs — himanshustwts · 2026-09-11