MathArena - Kangaroo 2025 Levels 11-12: leaderboard
Math Kangaroo 2025 problems for grades 11-12, covering advanced algebra, trigonometry, combinatorics, and competition-style problem solving.
Metric: Accuracy (%). Source: matharena.ai. Saturation forecast: Estimated already saturated. 23 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.8 (Max) | 100 | #37 (Claude Opus 4.8) |
| 2 | GPT-5.5 (xHigh) | 98.33 | #31 (GPT-5.5) |
| 3 | GPT-5.4 (xHigh) | 98.33 | #79 (GPT-5.4) |
| 4 | Kimi K3 (Thinking) | 98.33 | #30 (Kimi K3) |
| 5 | Gemini 3.1 Pro (Preview) | 97.5 | #58 |
| 6 | Gemini 3 Pro (Preview) | 97.5 | #66 |
| 7 | Gemini 3.6 Flash | 96.67 | #51 |
| 8 | Gemini 3 Flash | 95.83 | #99 |
| 9 | GPT-5.2 (High) | 95.83 | #110 (GPT-5.2) |
| 10 | GPT-5 (High) | 95 | #98 (GPT-5) |
| 11 | Gemini 3.5 Flash | 93.33 | #60 |
| 12 | Qwen 3.5 397B A17B | 91.67 | #146 |
| 13 | GPT-5.1 (High) | 91.67 | #135 (GPT-5.1) |
| 14 | Kimi K2.5 (Thinking) | 90 | #144 (Kimi K2.5) |
| 15 | Gemini 2.5 Pro | 89.17 | #152 |
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-11-12 · How It Works · Data refreshed daily, snapshot 2026-10-20.