Kangaroo 2025 11-12
Math · 2025-10-20
This MathArena track evaluates models on the Kangaroo 2025 11-12 problem set. Scores report the percentage of problems answered correctly.
Top models (higher is better)
| Model | Score |
|---|---|
| Opus 4.8 | 100.0 |
| GPT-5.4 | 98.3 |
| GPT-5.5 | 98.3 |
| Kimi K3 | 98.3 |
| Gemini 3.1 Pro Preview | 97.5 |
| Gemini 3 Pro Preview | 97.5 |
| Gemini 3.6 Flash | 96.7 |
| Gemini 3 Flash Preview | 95.8 |
| GPT-5.2 | 95.8 |
| GPT-5 | 95.0 |
| Gemini 3.5 Flash | 93.3 |
| GPT-5.1 | 91.7 |
| Qwen3.5 397B A17B | 91.7 |
| Kimi K2.5 | 90.0 |
| Gemini 2.5 Pro | 89.2 |
| Opus 4.6 | 87.5 |
| Sonnet 4.5 | 87.5 |
| Qwen3-VL-235B-A22B-Instruct | 85.8 |
| GPT-5 Mini | 85.0 |
| Grok 4.1 Fast | 81.7 |
| Grok 4 Fast | 80.8 |
| GLM-4.5V | 78.3 |
| Grok 4 | 76.7 |