MathArena - Kangaroo 2025 Levels 1-2 — leaderboard
Metric: Accuracy (%). Source: matharena.ai. 21 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Human Expert | 100 |
| 2 | GPT-5.5 (xHigh) | 95.83 |
| 3 | GPT-5.4 (xHigh) | 94.79 |
| 4 | Gemini 3.5 Flash | 89.58 |
| 5 | Gemini 3 Flash | 87.5 |
| 6 | Gemini 3.1 Pro (Preview) | 86.46 |
| 7 | Qwen 3.5 397B A17B | 81.25 |
| 8 | GPT-5.2 (High) | 80.21 |
| 9 | Gemini 3 Pro (Preview) | 76.04 |
| 10 | Kimi K2.5 (Thinking) | 76.04 |
| 11 | Median Human | 75 |
| 12 | Claude Opus 4.8 (Max) | 70.83 |
| 13 | GPT-5 (High) | 68.75 |
| 14 | GPT-5.1 (High) | 65.62 |
| 15 | GLM-4.5V | 65.62 |
Interactive version: theaggregate.ai/benchmark?slug=matharena-kangaroo-2025-levels-1-2 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.