TRACER: leaderboard
Data contamination is a known threat to the reliability of model evaluation. However, it remains underexplored in code large language models (LLMs), where contamination often goes beyond exact duplication. We present TRACER, a semantic-aware framework for fine-grained code contamination detection. TRACER models contamination using three levels of semantic overlap - Functionally Identical, Nearly I
Metric: F1 Score (self-reported). Source: benchmarklist.com. Saturation forecast: Around November 2026. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 91 | #98 |
| 2 | Gemini 2.5 Pro | 81 | #152 |
| 3 | GPT-OSS-120B | 78 | #341 |
| 4 | Qwen 3 14B | 72 | #537 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=tracer · How It Works · Data refreshed daily, snapshot 2026-10-20.