NVIDIA LLM Robustness - AGIEval Consistency — leaderboard
Metric: Consistency (%). Source: huggingface.co. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 3 70B Instruct | 83.13 |
| 2 | Llama 3.1 70B Instruct | 81.79 |
| 3 | Mistral Large 2 (Jul) | 75.77 |
| 4 | Yi 1.5 34B Chat | 69.95 |
| 5 | Llama 3.1 8B Instruct | 62.54 |
| 6 | Mistral Nemo Instruct (2407) | 58.7 |
Interactive version: theaggregate.ai/benchmark?slug=nvidia-llm-robustness-agieval-consistency · How the rankings work · Data refreshed daily, snapshot 2026-07-22.