humanitys_last_exam.jsonl

{"model": "gpt-4o", "score": 3.1}
{"model": "grok-2", "score": 3.9}
{"model": "claude-3-5-sonnet", "score": 4.8}
{"model": "gemini-2.0-flash-thinking", "score": 7.2}
{"model": "o1", "score": 7.2}