LogicKor - Math: leaderboard
Metric: Score (0-10). Source: lk.instruct.kr. 253 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 1.5 Pro (001) | 9.28 |
| 2 | GPT-4o (2024-05-13) | 9.21 |
| 3 | Claude 3.5 Sonnet (20240620) | 9.07 |
| 4 | Mistral Large 2 (Jul) | 8.85 |
| 5 | Gemini 1.5 Flash (001) | 8.78 |
| 6 | GPT-4 Preview (1106) | 8.28 |
| 7 | GPT-4 Preview (0125) | 8.21 |
| 8 | Llama 3.1 405B Instruct FP8 | 8 |
| 9 | Qwen 2 72B Instruct | 7.78 |
| 10 | Llama-VARCO-8B-Instruct | 7.78 |
| 11 | GPT-4 Turbo | 7.64 |
| 12 | ko-gemma-2-9B-it | 7.57 |
| 13 | Claude 3 Opus (20240229) | 7.42 |
| 14 | Claude 3 Haiku (20240307) | 7.07 |
| 15 | GPT-4 (0613) | 7.07 |
Interactive version: theaggregate.ai/benchmark?slug=logickor-math · How It Works · Data refreshed daily, snapshot 2026-09-05.