New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
CNMO 2024 benchmark
AI model leaderboard for the CNMO 2024 benchmark. Compare how large language models score on CNMO 2024, see the full ranking, and understand what this AI benchmark measures. Qwen3-235B-A22B-Thinking (Jul 2025) currently leads with 89.5%. Chinese National Mathematical Olympiad 2024 — high-difficulty Chinese olympiad problems.
Leaderboard
| # | Model | Organization | Score | Variant | Source |
|---|---|---|---|---|---|
| #1 | Qwen3-235B-A22B-Thinking (Jul 2025) | Qwen | 89.5% | thinking-cited-ring-1t | official ↗ |
| #2 | Ring-1T | Ant Group | 88.54% | thinking | official ↗ |
| #3 | GPT-5 | OpenAI | 87.93% | thinking-high-cited-ring-1t | official ↗ |
| #4 | DeepSeek-V3.1-Terminus | DeepSeek | 85.42% | thinking-cited-ring-1t | official ↗ |
| #5 | gemini-2.5-pro | Google DeepMind | 80.64% | cited-ring-1t | official ↗ |
| #6 | Ling-1T | Ant Group | 79.25% | pass@1 | official ↗ |
| #7 | gemini-2.5-pro | Google DeepMind | 74.65% | lowthink-cited-ling-1t | official ↗ |
| #8 | DeepSeek-V3.1-Terminus | DeepSeek | 73.78% | non-thinking-cited-ling-1t | official ↗ |
| #9 | Pangu Pro MoE | Huawei | 70.8% | instruct-pass@1 | official ↗ |
| #10 | Kimi K2 | Moonshot | 68.92% | instruct-0905-cited-ling-1t | official ↗ |
| #11 | GPT-5 | OpenAI | 63.11% | main-cited-ling-1t | official ↗ |
| #12 | dots.llm1 | Rednote | 40.6% | pass@1 | official ↗ |
| #13 | DeepSeek-V3 | DeepSeek | 33.9% | pass@1 | official ↗ |
| #14 | Llama 4 Scout | Meta AI | 20.4% | pass@1-cited-pangu-pro-moe | official ↗ |
Frequently asked questions about CNMO 2024
What is the CNMO 2024 benchmark?
Chinese National Mathematical Olympiad 2024 — high-difficulty Chinese olympiad problems.
How is the CNMO 2024 benchmark scored?
CNMO 2024 is scored using the pass@1 (%) metric, where a higher score is better. The maximum achievable score is 100.000. GenAIList aggregates reported scores from model providers and papers into a single ranked leaderboard.
Which AI model scores highest on CNMO 2024?
As of the latest reported scores on GenAIList, Qwen3-235B-A22B-Thinking (Jul 2025) achieves the highest result on CNMO 2024 with a score of 89.5%.
Is a higher CNMO 2024 score better?
Yes. On CNMO 2024 a higher score indicates better performance, so models near the top of the leaderboard are the strongest.