MedMeta - Title Only (Chain-of-Thought): leaderboard
Metric: LLM-judge score (0-5; mean of Gemini 2.5 Pro, o4-mini and Qwen3-235B judges rating semantic equivalence of the generated conclusion to the meta-analysis's own, 81 meta-analyses; Parametric-CoT: sub-questions answered from the model's own knowledge with a self-feedback loop). Source: arxiv.org. Saturation forecast: Estimated already saturated. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Flash | 2.9 |
| 2 | O4 Mini | 2.7 |
| 3 | Qwen 3 8B (Non-reasoning) | 2.27 |
| 4 | Qwen 3 8B (Thinking) | 2 |
| 5 | DeepSeek R1 0528 Qwen3 8B | 1.94 |
| 6 | Gemma 3 27B | 1.77 |
Interactive version: theaggregate.ai/benchmark?slug=medmeta-title-only-chain-of-thought · How It Works · Data refreshed daily, snapshot 2026-09-25.