Skip to content
← All posts

Six of six at IMO 2026, on two different backends

A fully agentic, YOLO-style run solved every problem of the 2026 International Mathematical Olympiad, machine-checked in Lean 4 — 3.2× faster than the previously reported agentic result, with both backends closing all six.

All six problems of the 2026 International Mathematical Olympiad, solved by a fully agentic, YOLO-style run with no human in the turn, and every solution formally verified by Lean 4. There is no rubric here and no benefit of the doubt: the kernel accepts the proof or it does not.

Two workers were run independently. Both closed all six.

The times

API time — the time actually spent inside model calls, which is the only measure that does not reward a slower harness — against the times reported by AxiomProver on the same statements.

ProblemHumanfia (GPT-5.6)Humanfia (Kimi-K3)AxiomProver
Q133.6 min77.7 min24 min
Q296.2 min220.2 min360 min
Q3179.4 min338.4 min869 min
Q453.3 min65.6 min39 min
Q542.4 min86.7 min65 min
Q662.7 min209.0 min139 min
Total467.6 min · 3.2×997.6 min1,496 min

The shape of that table is the point. On Q1 and Q4 — the two easiest problems — we lose. On Q3, which is the hardest, we win by nearly five times. A loop earns its keep exactly where the work is long enough for the loop to matter, and nowhere else; on a problem a strong model closes in twenty minutes, the arrangement around it is overhead.

What is released

The formal statements, both sets of Lean solutions and the scripts that reproduce the solving process. Pinned to Lean 4.31.0 and Mathlib.

humanfia/imo2026 · AxiomMath/IMO2026 · HOA