LingxiDiagBench (Static, Clinical) - Next-Question BLEU: leaderboard
Metric: BLEU (%, 0-100, character-level tokens) of the predicted next doctor question against the real psychiatrist's question, given the consultation so far; LingxiDiag-Clinical transcribed outpatient consultations, zero-shot; higher is better. Source: arxiv.org. Saturation forecast: Not forecast. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 1.7B | 33.5 | #1186 |
| 2 | Qwen 3 4B | 33.4 | #823 |
| 3 | GPT-OSS-20B | 33.1 | #499 |
| 4 | Qwen 3 8B | 32.3 | #667 |
| 5 | Qwen 3 32B | 32.1 | #424 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=lingxidiagbench-static-clinical-next-question-bleu · How It Works · Data refreshed daily, snapshot 2026-10-11.