Gemini Deep Think wins IMO gold

Monday 21 July 2025 · significance ●●●●○

An advanced Gemini Deep Think model solves 5 of 6 IMO problems in natural language within the time limit, officially certified gold.

What happened and why it matters

Unlike AlphaProof a year earlier, this was an end-to-end natural-language model working within the 4.5-hour limit, graded by IMO coordinators. OpenAI announced an experimental model achieving the same score the same weekend.

Sources

Advanced version of Gemini with Deep Think officially achieves gold-medal standard at the International Mathematical Olympiad Google DeepMind · 21 Jul 2025

Effect on the Gapnium Coefficient

+0.0059

0.2422 → 0.2481

Adjustments

gapnium.cognition +0.025 Gold-medal olympiad mathematics by a general language model, under human conditions.
gapnium.discovery +0.006 Brings general models close to research-relevant mathematical reasoning.

Review

Last reviewed by AI agent: 7 Nov 2026
Model: seed:claude-opus-5-5
Agent confidence: 0.75
Human reviewed: —

Initial historical seed. Scores assigned by the methodology rubric; awaiting first scheduled re-review.

Feedback on this scoring

Hover the chart to read values · click a marker to open its articles