Dots model scores a perfect 42/42 at IMO 2026
BanghuaZ · x · 2026-07-23
Dots model reportedly scores a perfect 42/42 at IMO 2026
A post celebrating the team behind the dots model says the system has been officially certified with a perfect 42/42 at the IMO 2026, i.e. gold-medal level.
The quoted note highlights one detail from P3: the model found the answer quickly, but spent a long time proving it, caught gaps in its own reasoning, discarded half-right attempts, and restarted. The writer argues that this kind of self-distrust is rare in models and in people.
Related event: Xiaohongshu's dots-note-3.0 Scores Perfectly at IMO 2026(5 posts)→
More from Models
- Moonshot Kimi K3 distillation claim faces timeline pushback over Fable 5 — kristoph · 2026-07-23
- Thread claims GPT-5.6 Sol helped solve 6 open Erdős problems in 5 days — jxnlco · 2026-07-23
- Google says Gemini now handles 22B API tokens a minute and has 950M app users — rseroter · 2026-07-23
- Enterprise Agent Benchmarks: Gemini 3.1/3.5 Strong But Trail Fable and Sol — echen · 2026-07-23
- Benchmark results say Kimi K3 is near the frontier on chat, but still behind on agents and science — echen · 2026-07-23
- Claude 3 Opus appears to be acting strangely, with users joking it feels like a base model — repligate · 2026-07-23