LLM2014 Logic 2024-06 — leaderboard
Metric: Score (%). Source: raw.githubusercontent.com. 30 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4 Turbo | 76.53 |
| 2 | DeepSeek Coder V2 | 58.35 |
| 3 | Claude 3 Opus | 54.51 |
| 4 | Yi Large | 51.8 |
| 5 | Qwen 2 72B | 47.91 |
| 6 | GPT-4 (0613) | 46.61 |
| 7 | DeepSeek V2 | 39.49 |
| 8 | Gemini 1.5 Pro | 37.49 |
Interactive version: theaggregate.ai/benchmark?slug=llm2014-logic-2024-06 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.