Reported in recent model launches
These model reports include this benchmark. Their harnesses, task subsets, scoring policies, and resource budgets can differ; follow each report’s evaluation notes before joining the numbers.
What it measures
A new annual contest set tests mathematical reasoning through short integer answers.
How to read the result
Report the correct-count denominator and sampling budget. Averaged repeated attempts can produce a finer percentage than a single exam run.
Limits and comparison traps
Keep 2026 separate from 2025 and older sets. Saturated answer accuracy does not establish valid proofs or research-level mathematics.
Benchmark reference notes
30 problems from the 2026 American Invitational Mathematics Examination (I & II).
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
Pin the benchmark release, task split, model configuration, tools, sampling budget, and evaluation harness described by the primary source.
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.
PRIMARY EVIDENCE & FURTHER READING
Reviewed 2026-10-26. Explanation and interpretation by RLTasks. Benchmark ownership remains with its original authors.