NovGauge - Multi-Paper Grouping - Task F1: leaderboard
Metric: F1 (%). Source: arxiv.org. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.6 | 78.8 |
| 2 | GPT-5.5 | 77.1 |
| 3 | Claude Opus 4.7 | 77.1 |
| 4 | Gemini 3.1 Pro (Preview) | 75.5 |
| 5 | Qwen 3.6 Plus | 75.5 |
| 6 | Gemini 3.1 Flash Lite | 75.4 |
| 7 | Kimi K2.6 | 68.6 |
| 8 | GLM-5.1 | 65.8 |
| 9 | MiniMax-M2.7 | 62 |
| 10 | GPT-5.4 Mini | 60.4 |
| 11 | DeepSeek V4 Pro | 57.9 |
| 12 | DeepSeek V4 Flash | 53.7 |
Interactive version: theaggregate.ai/benchmark?slug=novgauge-multi-paper-grouping-task-f1 · How It Works · Data refreshed daily, snapshot 2026-09-19.