KORGym - Mathematical and Logical — leaderboard
Metric: Score. Source: razor233.github.io. 19 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro (03-25) | 0.93 |
| 2 | O3 Mini | 0.79 |
| 3 | DeepSeek R1 | 0.69 |
| 4 | O1 (2024-12-17) | 0.65 |
| 5 | Qwen 3 32B (Thinking) | 0.58 |
| 6 | Claude 3.7 Sonnet (Thinking) | 0.52 |
| 7 | DeepSeek R1 Distill Qwen 32B | 0.35 |
| 8 | Gemini 2.0 Flash (Thinking) | 0.34 |
| 9 | DeepSeek V3 (0324) | 0.27 |
| 10 | Gemini 2.0 Flash | 0.17 |
| 11 | Doubao-1.5-Pro | 0.16 |
| 12 | GPT-4o | 0.08 |
| 13 | DeepSeek-R1-Distill-Qwen-7B | 0.06 |
| 14 | Qwen 2.5 72B Instruct | 0.04 |
| 15 | Qwen 2.5 32B Instruct | 0.04 |
Interactive version: theaggregate.ai/benchmark?slug=korgym-mathematical-and-logical · How the rankings work · Data refreshed daily, snapshot 2026-07-22.