Making A Leaderboard
| AI TOOL | % Accuracy | Model |
|---|---|---|
| Gemini 1.5 Pro | 96.00% | Google Model |
| GPT-4 O1 | 94.00% | OpenAI Model |
| Claude 3 Opus | 92.00% | Anthropic Models |
| GPT-4 Turbo | 92.00% | OpenAI Model |
| GPT-4 | 92.00% | OpenAI Model |
| Gemini 1.5 Flash | 84.00% | Google Models |
| Claude 3 Sonnet | 76.00% | Anthropic Model |
| Claude 2.1 | 72.00% | Anthropic Model |
| Gemini 2.0 Flash (Beta) | 28.00% | Google Models |