// BENCHMARK

UGMathBench benchmark

AI model leaderboard for the UGMathBench benchmark. Compare how large language models score on UGMathBench, see the full ranking, and understand what this AI benchmark measures. GPT-5 currently leads with 80.18. Undergraduate-level mathematics benchmark — calculus, linear algebra, probability, etc.

Leaderboard

# Model Organization Score Variant Source
#1 GPT-5 OpenAI 80.18 thinking-high-cited-ring-1t official ↗
#2 DeepSeek-V3.1-Terminus DeepSeek 77.19 thinking-cited-ring-1t official ↗
#3 Qwen3-235B-A22B-Thinking (Jul 2025) Qwen 77 thinking-cited-ring-1t official ↗
#4 Ring-1T Ant Group 76.47 thinking official ↗
#5 Ling-1T Ant Group 74.95 official ↗
#6 gemini-2.5-pro Google DeepMind 74.5 cited-ring-1t official ↗
#7 DeepSeek-V3.1-Terminus DeepSeek 72.7 non-thinking-cited-ling-1t official ↗
#8 gemini-2.5-pro Google DeepMind 70.1 lowthink-cited-ling-1t official ↗
#9 Kimi K2 Moonshot 69.97 instruct-0905-cited-ling-1t official ↗
#10 GPT-5 OpenAI 67.27 main-cited-ling-1t official ↗

Frequently asked questions about UGMathBench

What is the UGMathBench benchmark?

Undergraduate-level mathematics benchmark — calculus, linear algebra, probability, etc.

How is the UGMathBench benchmark scored?

UGMathBench 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 UGMathBench?

As of the latest reported scores on GenAIList, GPT-5 achieves the highest result on UGMathBench with a score of 80.18.

Is a higher UGMathBench score better?

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