Mathematics · Benchmark profile
An independently evaluated AIME 2025 result from Artificial Analysis.
Data verified 27 Jul 2026 · Methodology 1.8.0
Benchmark score on Artificial Analysis AIME 2025
GPT-5.2 leads at 99%, followed by GPT-OSS 120B (93.4%).
2 ranked models · higher is better · labels show rank and score
| Model | Rank | Provider | Score |
|---|---|---|---|
| GPT-5.2 | #1 | OpenAI | 99% |
| GPT-OSS 120B | #2 | OpenAI | 93.4% |
One best score per model · higher is better
| Rank | Model | Provider | License | Evidence use | Score |
|---|---|---|---|---|---|
| #1 | GPT-5.2 gpt-5.2 | OpenAI | closed | Estimated reference | 99% |
| #2 | GPT-OSS 120B gpt-oss-120b | OpenAI | open | Reference only | 93.4% |
About Artificial Analysis AIME 2025
An independently evaluated AIME 2025 result from Artificial Analysis. Results stay tied to the exact model variant and evaluation system. Multiple systems for the same model use the best published score on this page; overall Lumina scoring uses the median of ranking-eligible rows.
Open benchmark source ↗FAQ
An independently evaluated AIME 2025 result from Artificial Analysis.
GPT-5.2 by OpenAI currently leads with 99%.
2 models in the LuminaBench cohort have a qualifying score on this benchmark.
No. This benchmark is display-only and does not enter the overall Lumina composite.
Related
