MedConclusion - Formality Similarity: leaderboard
MedConclusion (2026) biomedical conclusion generation from PubMed structured abstracts, judged by GPT-5.4-mini for formality similarity with the author-written conclusion on a 0-100 scale over a random 30K-abstract subset; higher is better.
Metric: Formality similarity (judge score 0-100): the model writes a formal academic conclusion (prompt A, no length or style constraint) from the non-conclusion sections of a PubMed structured abstract; a GPT-5.4-mini judge scores it 0-100 against the author-written conclusion, averaged over a random 30K-abstract subset of MedConclusion; temperature 0, at most 1,024 new tokens; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 15 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GPT-5.4 | Non-reasoning | 89.8 | #135 |
| 2 | Gemini 3.1 Pro (Preview) | 89.49 | #99 | |
| 3 | Gemma 3 27B (IT) | 89.36 | #1324 | |
| 4 | Gemini 3 Flash | Non-reasoning | 89.17 | #175 |
| 5 | GLM-4.6V | 88.87 | #710 | |
| 6 | MiniMax-M2.1 | 88.83 | #575 | |
| 7 | Kimi K2 (Thinking) | 88.62 | ||
| 8 | DeepSeek V3.2 | Non-reasoning | 88.59 | #419 |
| 9 | Qwen 3 4B 2507 Instruct | 88.47 | #2221 | |
| 10 | Gemma 2 9B (IT) | 88.41 | #2369 | |
| 11 | Llama 3.1 8B Instruct | 88.03 | #4600 | |
| 12 | Qwen 2.5 VL 7B Instruct | 87.34 | #1902 | |
| 13 | Qwen 2.5 7B Instruct | 86.6 | #2723 | |
| 14 | Llama 3.2 1B Instruct | 78.35 | #9022 | |
| 15 | DeepSeek R1 | 75.91 | #482 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=medconclusion-formality-similarity · How It Works · Data refreshed daily, snapshot 2026-11-21.