NovBench - Correctness: leaderboard
Metric: Correctness (DistAcc, 0-1): one minus half the L1 distance between the positive, neutral and negative proportions of the generated statements and of the human comments; 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 | Qwen 3 14B | 0.66 |
| 2 | Qwen 3 8B | 0.66 |
| 3 | DeepSeek R1 Distill Llama 70B | 0.66 |
| 4 | Qwen 3 32B | 0.66 |
| 5 | DeepSeek R1 Distill Qwen 14B | 0.64 |
| 6 | Gemini 2.5 Flash | 0.6 |
| 7 | GPT-OSS-20B | 0.58 |
| 8 | GPT-5 | 0.48 |
| 9 | GPT-OSS-120B | 0.44 |
Interactive version: theaggregate.ai/benchmark?slug=novbench-correctness · How It Works · Data refreshed daily, snapshot 2026-10-07.