NovBench - Relevance: leaderboard
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; 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. 19 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o | 3.7 |
| 2 | Qwen 3 8B | 3.58 |
| 3 | DeepSeek R1 Distill Llama 70B | 3.49 |
| 4 | Qwen 3 32B | 3.47 |
| 5 | Gemini 2.5 Flash | 3.47 |
| 6 | DeepSeek R1 Distill Qwen 14B | 3.41 |
| 7 | Qwen 3 14B | 3.39 |
| 8 | GPT-OSS-20B | 3.32 |
| 9 | GPT-5 | 3.28 |
| 10 | GPT-OSS-120B | 3.26 |
Interactive version: theaggregate.ai/benchmark?slug=novbench-relevance · How It Works · Data refreshed daily, snapshot 2026-10-07.