NovBench (RAG) - Relevance: 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. 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; 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: Around July 2028. 19 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1SEA-S3.52
2Gemini 2.5 Flash3.51#463
3GPT-4o3.45#751
4SEA-E3.38
5Qwen 3 8B3.3#1873
6Qwen 3 32B3.26#972
7GPT-53.23#178
8Qwen 3 14B3.2#1269
9GPT-OSS-120B3.14#704
10GPT-OSS-20B3.14#1183
11DeepSeek R1 Distill Qwen 14B3.07#2771
12DeepSeek R1 Distill Llama 70B3.04#1669
13CycleReviewer-70B3.03#1880
14CycleReviewer-8B2.89
15DeepReviewer-14B2.73#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-rag-relevance · How It Works · Data refreshed daily, snapshot 2026-11-21.