Repost claims Claude Opus 5 scored a perfect 42/42 on IMO 2026 problems
inductionheads · x · 2026-07-25
A repost claims that Claude Opus 5 solved the IMO 2026 set with a perfect 42/42 score, described as gold-medal level performance.
- The run reportedly used no agent harness or tools.
- The screenshot says the model produced four independent solutions per problem across six problems, and all 24 solutions were judged correct by a panel of models.
- Human experts also graded one pre-specified solution per problem as correct, yielding 7/7 on each problem and a total of 42/42, above the stated gold cutoff of 29/42.
Related event: Rumor Claims Claude Opus 5 Achieves Perfect 2026 IMO Score Without Tools(5 posts)→
More from Models
- Daily AI brief: GPT-Live-1 in API, OpenAI pauses $200 Pro signups amid Astra demand — koltregaskes · 2026-09-11
- 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