HELM TORR - Tablebench Numerical Reasoning - Robustness: leaderboard
Metric: Robustness (0-100). Source: crfm.stanford.edu. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Mistral 7B Instruct (v0.3) | 71.09 |
| 2 | Llama 3.1 8B Instruct | 65.54 |
| 3 | Qwen 2 72B Instruct | 55.4 |
| 4 | GPT-4o Mini (2024-07-18) | 54.92 |
| 5 | Gemini 1.5 Flash (002) | 54.45 |
| 6 | Claude 3.5 Haiku (20241022) | 54.07 |
| 7 | GPT-4o (2024-11-20) | 51.12 |
| 8 | Llama 3.1 405B Instruct | 50.7 |
| 9 | Gemini 1.5 Pro (002) | 50.65 |
| 10 | Llama 3.1 70B Instruct | 49.2 |
| 11 | Claude 3.5 Sonnet (20241022) | 43.54 |
| 12 | DeepSeek V3 | 42.62 |
Interactive version: theaggregate.ai/benchmark?slug=helm-torr-tablebench-numerical-reasoning-robustness · How It Works · Data refreshed daily, snapshot 2026-09-19.