SciFigPlag-Bench - Reuse-Type Classification: leaderboard
SciFigPlag-Bench (2026) reuse-type classification: name what content of a source figure was reused and the exact set of transformations applied. Joint accuracy in percent, higher is better.
Metric: Joint accuracy (%; the reused-content label and the exact set of modification labels must both be correct; SciFigPlag-Bench pairs of source and suspicious scientific figures (2,582 plagiarized pairs from documented real cases and taxonomy-guided synthesis, 2,541 visually similar negatives); the same task-specific prompts for every model, temperature 0). Source: arxiv.org. Saturation forecast: Around February 2027. 16 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash | 71.7 | #164 |
| 2 | Gemma 4 31B (IT) | 70.6 | #342 |
| 3 | Qwen 3.5 35B A3B | 69.8 | #482 |
| 4 | Qwen 3.6 35B A3B | 68.4 | #462 |
| 5 | GPT-5.4 | 65.5 | #123 |
| 6 | Gemma 4 26B A4B (IT) | 58.8 | #549 |
| 7 | Claude Sonnet 4.6 | 51.7 | #161 |
| 8 | Mistral Small 4 | 41.9 | #1201 |
| 9 | Qwen 3.5 2B | 17.9 | #4810 |
| 10 | Gemma 3 4B (IT) | 17.6 | #3831 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=scifigplag-bench-reuse-type-classification · How It Works · Data refreshed daily, snapshot 2026-11-13.