FrontierMath Tier 4
The hardest FrontierMath tier — 48 problems that take expert mathematicians days. Epoch AI runs it.
Competition and research mathematics, graded on the final answer or the proof. One of 5 comparable tests in math, a category the Index averages.
Read with care. 48 problems: one problem is about 2 points. Same OpenAI commissioning disclosure as tiers 1 to 3.
Publisher: Epoch AI (internal runs)What a model is asked to do
Solve the hardest FrontierMath tier: problems that take expert mathematicians days.
For exampleCompute the exact value of an infinite series built from the coefficients of a modular form, and confirm it by a second method.
Why it matters. The deepest end of the set. Progress here signals genuinely new capability.
The example is original and illustrative, not an item from the dataset.
- Models scored here
- 51
- Who produced the numbers
- Run by Epoch AI
- Items graded
- n = 48 (2.1% each)
- Best published result
- 97.6%
- License
- CC BY 4.0 (via Epoch AI)
- Direction
- Higher is better
- Scale
- Published as a share of items solved. For the Index, each score is a share of the best published result (97.6%), so the frontier reads 100. Guessing earns nothing on this test, so no chance correction applies.
- Provenance
- Epoch AI ran the evaluation itself, under settings it documents per model, and publishes the log of every answer.
Snapshot September 8, 2026
Ranking on this test
51 models on FrontierMath Tier 4
Best published run per model, and how close each one comes to the best published result on this test (the frontier reads 100). Every number links to the publisher that produced it. Internal runs are marked and carry their run details on the model page. One item on this test is 2.1 points, so read gaps smaller than that as noise.
The best models, ranked here, working inside Theo.
28 of the models on this page run inside Theo today. Theo picks the right one for each step and always shows which engine answered.