BELLS — leaderboard
Metric: BELLS Score (%). Source: centresecuriteia.github.io. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4 | 91.7 |
| 2 | Claude 3.5 Sonnet | 89.3 |
| 3 | Grok 2 | 87.5 |
| 4 | Gemini 1.5 Pro | 84.5 |
| 5 | DeepSeek V3 | 83.2 |
| 6 | Mistral Large | 82.5 |
Interactive version: aibenchmarks.dev/benchmark?slug=bells · How the rankings work · Data refreshed daily, snapshot 2026-07-06.