HiEviDR-Bench (RAG): leaderboard
Metric: Overall score (0-100): sum of five 0-20 dimension scores (multimodal report quality, evidence traceability, and progressively gated citation, claim and answer scores) judged by Qwen3-VL-235B-A22B-Instruct against the hierarchical evidence graph, averaged over the Wikipedia and arXiv subsets; MLLM with RAG: one-pass report generation over the top-15 retrieved multimodal evidence items; higher is better. Source: arxiv.org. Saturation forecast: Around 2035. 16 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol | 38.35 |
| 2 | Gemma 4 31B (IT) | 37.76 |
| 3 | GPT-5 | 37.62 |
| 4 | Grok 4.5 | 36.82 |
| 5 | GPT-5 Mini | 36.74 |
| 6 | InternVL3.5-8B | 36.2 |
| 7 | Qwen 3.5 27B | 36.09 |
| 8 | gemma-4-E4B-it | 35.83 |
| 9 | Qwen 3 VL 8B Instruct | 35.54 |
| 10 | Qwen 3.5 35B A3B | 34.27 |
| 11 | Qwen 3.5 4B | 34 |
| 12 | Qwen 3.5 9B | 33.13 |
Interactive version: theaggregate.ai/benchmark?slug=hievidr-bench-rag · How It Works · Data refreshed daily, snapshot 2026-09-29.