HELM TORR - Turl Col Type - Robustness: leaderboard
Metric: Robustness (0-100). Source: crfm.stanford.edu. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 3.5 Sonnet (20241022) | 62.22 |
| 2 | Gemini 1.5 Flash (002) | 59.29 |
| 3 | GPT-4o (2024-11-20) | 57.76 |
| 4 | DeepSeek V3 | 56.08 |
| 5 | Qwen 2 72B Instruct | 51.58 |
| 6 | Claude 3.5 Haiku (20241022) | 51.26 |
| 7 | Llama 3.1 70B Instruct | 50.94 |
| 8 | GPT-4o Mini (2024-07-18) | 50.64 |
| 9 | Gemini 1.5 Pro (002) | 50.6 |
| 10 | Llama 3.1 405B Instruct | 49.82 |
| 11 | Mistral 7B Instruct (v0.3) | 27.36 |
| 12 | Llama 3.1 8B Instruct | 18.87 |
Interactive version: theaggregate.ai/benchmark?slug=helm-torr-turl-col-type-robustness · How It Works · Data refreshed daily, snapshot 2026-09-19.