Glossary
OTIS Mock AIME
OTIS Mock AIME, on the Epoch AI leaderboard (CC BY 4.0, latest version we checked), is a set of math problems in the style of the US AIME olympiad, in a practice version built so the model cannot lean on answers it may already have seen. The score is the share of correct answers.
What it measures
OTIS Mock AIME, on the Epoch AI leaderboard (CC BY 4.0, latest version we checked), is a set of math problems in the style of the US AIME olympiad, in a practice version built so the model cannot lean on answers it may already have seen. The score is the share of correct answers.
When it matters
It helps when the task is calculation, logic or a problem with an exact answer, like closing a figure or checking a formula. It tells you little about writing, tone or customer support.
How to read it
Each problem has one exact numeric answer, on the Epoch AI leaderboard, in the latest version we checked. A gap of a few points can be just one or two questions.
Who leads
- Claude Opus 5.5 Anthropic100%
- Claude Sonnet 5.5 Anthropic100%
- GPT-6.1 Sol OpenAI100%
- GPT-6 Astra OpenAI100%
- GPT-5.5 OpenAI100%
- Gemini 4 Argon Google100%
- Qwen3.8 Max Alibaba100%
- Kimi K3.1 Pro Moonshot AI100%
- Claude Fable 5 Anthropic100%
- Claude Fable 5.1 Anthropic100%
Source: Epoch AI, latest version we checked.