Question Answering on Probe 2
70AccuracyChatGPT 5 Thinking
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| ChatGPT 5 Thinking2026.01 | 70 | — | — | |
| Gemini 2.5 Pro2026.01 | 62.7 | — | — | |
| Anthropic Claude-3-Haiku2026.01 | 61 | — | — | |
| Naive Humanmedical knowledge=none2026.01 | 27.3 | — | — |
| Method | Links | |||
|---|---|---|---|---|
| ChatGPT 5 Thinking2026.01 | 70 | — | — | |
| Gemini 2.5 Pro2026.01 | 62.7 | — | — | |
| Anthropic Claude-3-Haiku2026.01 | 61 | — | — | |
| Naive Humanmedical knowledge=none2026.01 | 27.3 | — | — |