NovBench (Few-Shot) - Relevance: leaderboard
NovBench novelty assessment of EMNLP 2023 papers with a few-shot prompt with two analogous NovBench examples. Relevance is how well the generated assessment covers each novelty claim, as an information-matching score from 0 to 5, higher is better.
Metric: Relevance (AvgIMS, 0-5; the paper states a 1-5 scale but prints values below 1): for each novelty-description sentence the best information-matching score against any sentence of the generated evaluation, averaged; few-shot prompt with two analogous NovBench examples; 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. 19 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o | 3.56 | #754 |
| 2 | Gemini 2.5 Flash | 3.47 | #466 |
| 3 | DeepSeek-R1-8B (NovBench checkpoint unspecified) | 3.47 | |
| 4 | DeepSeek R1 Distill Llama 70B | 3.45 | #1676 |
| 5 | Qwen 3 32B | 3.42 | #983 |
| 6 | SEA-S | 3.41 | |
| 7 | Qwen 3 8B | 3.41 | #1890 |
| 8 | DeepSeek R1 Distill Qwen 14B | 3.38 | #2739 |
| 9 | Qwen 3 14B | 3.37 | #1284 |
| 10 | CycleReviewer-70B | 3.34 | #1899 |
| 11 | SEA-E | 3.34 | |
| 12 | GPT-OSS-20B | 3.33 | #1188 |
| 13 | GPT-5 | 3.31 | #185 |
| 14 | GPT-OSS-120B | 3.19 | #712 |
| 15 | CycleReviewer-8B | 3.08 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=novbench-few-shot-relevance · How It Works · Data refreshed daily, snapshot 2026-11-22.