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

#ModelScoreOverall rank
1GPT-4o3.56#754
2Gemini 2.5 Flash3.47#466
3DeepSeek-R1-8B (NovBench checkpoint unspecified)3.47
4DeepSeek R1 Distill Llama 70B3.45#1676
5Qwen 3 32B3.42#983
6SEA-S3.41
7Qwen 3 8B3.41#1890
8DeepSeek R1 Distill Qwen 14B3.38#2739
9Qwen 3 14B3.37#1284
10CycleReviewer-70B3.34#1899
11SEA-E3.34
12GPT-OSS-20B3.33#1188
13GPT-53.31#185
14GPT-OSS-120B3.19#712
15CycleReviewer-8B3.08

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.