AIME 2025 Benchmark

Explore score history ↗

AIME 2025 is an AI benchmark in the Benchmark Radar catalog.

Released: 2025-02-08
Openness: unknown
Importer: Benchmark Saturation

Source provenance

Original evidence

AIME 2025 results and reported scores

Reported benchmark scores · Benchmark Saturation

Reported scores: 5

Model	Organization	Reported value	Reported	Evidence
Gemini 3 Flash	—	97.0	—	evidence
Gemini 3 Preview (high)	—	95.7	—	evidence
GLM-4.7	—	95.0	—	evidence
GPT-5.2 (high)	—	99.0	—	evidence
MiMo-V2-Flash	—	96.3	—	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 AIME 2025?

AIME 2025