DrugDiscoveryBench — leaderboard
Metric: Score (%). Source: scale.com. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 51.6 |
| 2 | Gemini 3.5 Flash | 50 |
| 3 | Claude Opus 4.8 | 46.8 |
| 4 | GLM-5.2 | 36.2 |
| 5 | Kimi K2.7 Code | 35.3 |
| 6 | DeepSeek V4 Pro | 31.7 |
| 7 | Qwen 3.7 Max | 29.3 |
Interactive version: aibenchmarks.dev/benchmark?slug=drugdiscoverybench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.