HELM TORR - Wikitq - Robustness: leaderboard
Metric: Robustness (0-100). Source: crfm.stanford.edu. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 3.5 Sonnet (20241022) | 80.19 |
| 2 | DeepSeek V3 | 78.21 |
| 3 | Llama 3.1 405B Instruct | 76.09 |
| 4 | Llama 3.1 70B Instruct | 75.87 |
| 5 | Qwen 2 72B Instruct | 75.34 |
| 6 | GPT-4o (2024-11-20) | 75.33 |
| 7 | GPT-4o Mini (2024-07-18) | 73.3 |
| 8 | Gemini 1.5 Flash (002) | 72.33 |
| 9 | Gemini 1.5 Pro (002) | 69.01 |
| 10 | Llama 3.1 8B Instruct | 66.83 |
| 11 | Claude 3.5 Haiku (20241022) | 60.78 |
| 12 | Mistral 7B Instruct (v0.3) | 39.85 |
Interactive version: theaggregate.ai/benchmark?slug=helm-torr-wikitq-robustness · How It Works · Data refreshed daily, snapshot 2026-09-19.