Math (math 500) Benchmark

Explore score history ↗

Math (math 500) is an AI benchmark in the Benchmark Radar catalog.

Released: 2021-03-05
Openness: unknown
Importer: Benchmark Saturation

Source provenance

Original evidence

Math (math 500) results and reported scores

Reported benchmark scores · Benchmark Saturation

Reported scores: 5

Model	Organization	Reported value	Reported	Evidence
Claude Opus 4	—	98.2	—	evidence
DeepSeek R1	—	98.3	—	evidence
GLM-4.5	—	98.2	—	evidence
Grok-4	—	99.0	—	evidence
o3	—	99.2	—	evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.

Which sources cite Math (math 500)?

Math (math 500)