MathArena - Kangaroo 2025 Levels 1-2: leaderboard
Math Kangaroo 2025 competition problems for grades 1-2, covering elementary arithmetic and basic logical puzzles.
Metric: Accuracy (%). Source: matharena.ai. Saturation forecast: Around January 2027. 23 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 (xHigh) | 95.83 | #31 (GPT-5.5) |
| 2 | GPT-5.4 (xHigh) | 94.79 | #79 (GPT-5.4) |
| 3 | Kimi K3 (Thinking) | 93.75 | #30 (Kimi K3) |
| 4 | Gemini 3.5 Flash | 89.58 | #60 |
| 5 | Gemini 3 Flash | 87.5 | #99 |
| 6 | Gemini 3.1 Pro (Preview) | 86.46 | #58 |
| 7 | Gemini 3.6 Flash | 83.33 | #51 |
| 8 | Qwen 3.5 397B A17B | 81.25 | #146 |
| 9 | GPT-5.2 (High) | 80.21 | #110 (GPT-5.2) |
| 10 | Gemini 3 Pro (Preview) | 76.04 | #66 |
| 11 | Kimi K2.5 (Thinking) | 76.04 | #144 (Kimi K2.5) |
| 12 | Claude Opus 4.8 (Max) | 70.83 | #37 (Claude Opus 4.8) |
| 13 | GPT-5 (High) | 68.75 | #98 (GPT-5) |
| 14 | GLM-4.5V | 65.62 | #346 |
| 15 | GPT-5.1 (High) | 65.62 | #135 (GPT-5.1) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=matharena-kangaroo-2025-levels-1-2 · How It Works · Data refreshed daily, snapshot 2026-10-20.