// BENCHMARK

IMOAnswerBench benchmark

AI model leaderboard for the IMOAnswerBench benchmark. Compare how large language models score on IMOAnswerBench, see the full ranking, and understand what this AI benchmark measures. Gemini 3 Pro currently leads with 83.3. International Mathematical Olympiad answer-only benchmark — graded on numeric/short answers from IMO problems.

Leaderboard

# Model Organization Score Variant Source
#1 Gemini 3 Pro Google DeepMind 83.3 cited-deepseek-v3-2 official ↗
#2 Kimi K2 Thinking Moonshot 78.6 thinking-cited-deepseek-v3-2 official ↗
#3 Kimi K2 Thinking Moonshot 78.6 thinking-no-tools official ↗
#4 DeepSeek-V3.2 DeepSeek 78.3 thinking official ↗
#5 GPT-5 OpenAI 76 cited-deepseek-v3-2 official ↗
#6 Kimi K2 Moonshot 45.8 k2-0905-no-tools-cited-k2-thinking official ↗

Frequently asked questions about IMOAnswerBench

What is the IMOAnswerBench benchmark?

International Mathematical Olympiad answer-only benchmark — graded on numeric/short answers from IMO problems.

How is the IMOAnswerBench benchmark scored?

IMOAnswerBench is scored using the accuracy metric, where a higher score is better. GenAIList aggregates reported scores from model providers and papers into a single ranked leaderboard.

Which AI model scores highest on IMOAnswerBench?

As of the latest reported scores on GenAIList, Gemini 3 Pro achieves the highest result on IMOAnswerBench with a score of 83.3.

Is a higher IMOAnswerBench score better?

Yes. On IMOAnswerBench a higher score indicates better performance, so models near the top of the leaderboard are the strongest.