PhageBench - Completeness Estimation: leaderboard
Metric: Accuracy (%) on 1,000 four-option items grading a phage genome as complete, high, medium or low quality, 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 2029. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 (Medium) | 43.1 |
| 2 | Claude Sonnet 4.5 (Thinking) | 35.5 |
| 3 | Qwen 3 Max (Thinking) | 33.8 |
| 4 | Gemini 3 Flash (Medium) | 32.1 |
| 5 | GPT-4o Mini | 24.5 |
| 6 | GPT-OSS-120B | 24.2 |
Interactive version: theaggregate.ai/benchmark?slug=phagebench-completeness-estimation · How It Works · Data refreshed daily, snapshot 2026-10-07.