PaperFit-Bench — leaderboard
Metric: Compile (self-reported). Source: benchmarklist.com. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 | 100 |
| 2 | Claude Opus 4.6 | 100 |
| 3 | MiMo-V2.5-Pro | 100 |
| 4 | DeepSeek V4 Pro | 95 |
Interactive version: theaggregate.ai/benchmark?slug=paperfit-bench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.