Three frontier models reportedly score perfectly on an IMO-style math set
deedydas · x · 2026-07-21
The post says three frontier models achieved a perfect score on an IMO-related problem set, and includes the author’s disclaimers about reproducibility and sampling variance.
- The author says the work is fully documented in the repo and different attempts may produce different outcomes.
- No public web search was used.
- The model runs referenced all have cutoffs well before IMO 2026.
- Source links are provided for Lean (Axiom), Fable, Sol, Kimi K3, and the repo itself.
Related event: Multiple Frontier AI Models Achieve Perfect Scores in IMO 2026 Testing(6 posts)→
More from Models
- Same Echo Maze prompt, three frontier models: all passed visually but shipped the same hidden bug — eyishazyer · 2026-09-11
- Benchmark scores drop from 89% to 19% on new evals — how benchmaxxing breaks leaderboard trust — airesearch12 · 2026-09-11
- ChatGPT tells user their question is too hard and to 'accept dumber answers' — phido3000 · 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