NovBench (RAG) - Coverage: leaderboard
NovBench novelty assessment of EMNLP 2023 papers with a retrieval-augmented prompt with the five most similar ACL, EMNLP and NAACL 2019-2022 titles and abstracts. Coverage is the share of the expert reviewers novelty comments that a generated statement matches by embedding similarity, from 0 to 1, higher is better.
Metric: Coverage (0-1): the share of the consolidated human novelty comments matched by a generated statement with embedding cosine similarity above 0.7; retrieval-augmented prompt with the five most similar ACL, EMNLP and NAACL 2019-2022 titles and abstracts; 1,684 EMNLP 2023 papers: from the novelty-description sentences of the paper introduction (selected by GPT-5) the model writes a novelty evaluation as positive, neutral and negative statements, compared with the expert reviewers novelty comments (extracted by GPT-4o-mini, then deduplicated, consolidated and sorted by sentiment by GPT-4o); greedy decoding, at most 4,096 tokens; higher is better. Source: arxiv.org. Saturation forecast: Not forecast. 18 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | SEA-E | 0.2712 | |
| 2 | SEA-S | 0.2474 | |
| 3 | Gemini 2.5 Flash | 0.227 | #466 |
| 4 | Qwen 3 8B | 0.1732 | #1890 |
| 5 | DeepSeek R1 Distill Qwen 14B | 0.1713 | #2739 |
| 6 | Qwen 3 32B | 0.1692 | #983 |
| 7 | GPT-OSS-20B | 0.1676 | #1188 |
| 8 | GPT-5 | 0.1673 | #185 |
| 9 | Qwen 3 14B | 0.1673 | #1284 |
| 10 | GPT-OSS-120B | 0.1644 | #712 |
| 11 | CycleReviewer-70B | 0.1522 | #1899 |
| 12 | DeepSeek R1 Distill Llama 70B | 0.15 | #1676 |
| 13 | CycleReviewer-8B | 0.1336 | |
| 14 | DeepSeek-R1-8B (NovBench checkpoint unspecified) | 0.1284 | |
| 15 | DeepReviewer-14B | 0.1193 | #852 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=novbench-rag-coverage · How It Works · Data refreshed daily, snapshot 2026-11-22.