NovBench - Coverage: leaderboard
NovBench (2026) tests whether LLMs can write the novelty assessment of a research paper from the novelty claims in its introduction, on 1,684 EMNLP 2023 papers with expert peer reviews. 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; zero-shot prompt; 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 | 0.261 | |
| 2 | SEA-S | 0.2576 | |
| 3 | CycleReviewer-70B | 0.2198 | #1880 |
| 4 | Gemini 2.5 Flash | 0.212 | #463 |
| 5 | DeepSeek R1 Distill Llama 70B | 0.2074 | #1669 |
| 6 | Qwen 3 32B | 0.2065 | #972 |
| 7 | DeepSeek R1 Distill Qwen 14B | 0.2053 | #2771 |
| 8 | Qwen 3 8B | 0.1996 | #1873 |
| 9 | Qwen 3 14B | 0.1974 | #1269 |
| 10 | GPT-OSS-20B | 0.1843 | #1183 |
| 11 | GPT-OSS-120B | 0.1787 | #704 |
| 12 | DeepSeek-R1-8B (NovBench checkpoint unspecified) | 0.1603 | |
| 13 | GPT-5 | 0.1591 | #178 |
| 14 | CycleReviewer-8B | 0.1577 | |
| 15 | DeepReviewer-14B | 0.1173 | #844 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=novbench-coverage · How It Works · Data refreshed daily, snapshot 2026-11-21.