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
Mathematical reasoning is tested through diagrams, charts, scientific figures and other visual contexts.
How to read the result
Inspect visual perception and the subsequent reasoning as separate failure points. Pin the exact full or mini evaluation split.
Limits and comparison traps
Answer extraction and available tools influence measured accuracy. The mini split and full test should not share an unlabeled score.
Benchmark reference notes
6,141 visual mathematical reasoning examples across 28 multimodal datasets and 3 newly created sets (MathVista-mini = 1,000).
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.