FrontierMath (Tiers 1–3)
290 unpublished research-level math problems written by professional mathematicians, tiers 1–3. 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. Commissioned by OpenAI, which has access to much of the problem set; Epoch discloses this and keeps a holdout it does not share.
Publisher: Epoch AI (internal runs)What a model is asked to do
Solve unpublished research-level mathematics problems written by professional mathematicians (tiers 1 to 3).
For exampleDetermine how many distinct values a given arithmetic function takes over the first million integers, with a verifiable argument.
Why it matters. Problems that take a working mathematician hours. A score here is a score against the frontier of the field.
The example is original and illustrative, not an item from the dataset.
- Models scored here
- 61
- Who produced the numbers
- Run by Epoch AI
- Items graded
- n = 290 (0.3% each)
- Best published result
- 93.7%
- 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 (93.7%), 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
61 models on FrontierMath (Tiers 1–3)
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 0.3 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.