BeyondAIME

What it measures

Harder post-AIME olympiad benchmark designed to avoid saturation of AIME 2024/2025 (used in DAPO, VAPO, SAO/GLM-5.2).

Reading the measurement

A correct final answer, a complete proof and useful research progress are different achievements. Choose the one the task actually grades. Inspect the permitted computation, attempt budget and handling of invalid arguments before comparing models.

Published evaluation

Accuracy on the 100-item BeyondAIME competition-mathematics test. Integer answer grading differs from proof verification. Source-reported comparison values are retained; a blank Grok result is not a zero.

Where this fits in an evaluation suite

Final-answer accuracy, proof credit, and expert-reviewed research progress are distinct signals. A proof-aware evaluation should retain partial work and audit strong claims.

Start with a capability hypothesis, then choose a second test with a different failure mode. Keep the checkpoint, reasoning effort, agent tools, sampling policy, and scoring procedure fixed when measuring a training intervention. Record failures and missing outputs in the denominator.

A reproducible comparison

Accuracy on the 100-item BeyondAIME competition-mathematics test. Integer answer grading differs from proof verification. Source-reported comparison values are retained; a blank Grok result is not a zero.

Publish the exact run configuration, item coverage, score units, and available uncertainty. If a source supplies only an aggregate or a single run, preserve that limit. A new model name or a rounded score alone does not establish a capability improvement.