Question Answering on Probe 1
99AccuracyGemini 2.5 Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini 2.5 Pro2026.01 | 99 | |
| ChatGPT 5 Thinking2026.01 | 98 | |
| Anthropic Claude-3-Haiku2026.01 | 96 | |
| Naive Humanmedical knowledge=none2026.01 | 38 |
| Method | Links | |
|---|---|---|
| Gemini 2.5 Pro2026.01 | 99 | |
| ChatGPT 5 Thinking2026.01 | 98 | |
| Anthropic Claude-3-Haiku2026.01 | 96 | |
| Naive Humanmedical knowledge=none2026.01 | 38 |