PhageBench - Phage Contig Identification: leaderboard
Metric: Accuracy (%) on 1,200 two-option items telling phage contigs from bacterial, archaeal, plasmid, fungal, protozoan and non-phage viral DNA, each a raw-nucleotide multiple-choice question with shuffled options, zero-shot chain-of-thought prompting (reasoning models at reasoning effort medium with at most 2,048 reasoning tokens); higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash (Medium) | 70.83 |
| 2 | GPT-5.2 (Medium) | 70.75 |
| 3 | Claude Sonnet 4.5 (Thinking) | 57.92 |
| 4 | Qwen 3 Max (Thinking) | 57.42 |
| 5 | GPT-OSS-120B | 50.08 |
| 6 | GPT-4o Mini | 50 |
Interactive version: theaggregate.ai/benchmark?slug=phagebench-phage-contig-identification · How It Works · Data refreshed daily, snapshot 2026-10-07.