HELM MMLU - Human Aging: leaderboard
The "Human Aging" subtask of HELM MMLU. HELM Classic MMLU group leaderboard from the public HELM release artifacts.
Metric: EM. Source: crfm.stanford.edu. Saturation forecast: Estimated already saturated. 79 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude 3.5 Sonnet (20240620) | 88.79 | #298 |
| 2 | Claude 3.5 Sonnet (20241022) | 86.1 | #291 |
| 3 | DeepSeek V3 | 86.1 | #323 |
| 4 | Claude 3 Opus (20240229) | 86.1 | #413 |
| 5 | GPT-4 Turbo (Preview) | 85.65 | #399 |
| 6 | GPT-4o (2024-08-06) | 84.75 | #335 |
| 7 | GPT-4 Turbo | 84.75 | #406 |
| 8 | GPT-4o (2024-05-13) | 84.3 | #326 |
| 9 | Llama 3.1 405B Instruct | 84.3 | #461 |
| 10 | Gemini 1.5 Pro (002) | 83.86 | #350 |
| 11 | Llama 3.2 90B Vision Instruct | 83.41 | #626 |
| 12 | GPT-4 (0613) | 83.41 | #494 |
| 13 | Nova Pro | 82.96 | #573 |
| 14 | Llama 3 70B | 82.51 | #635 |
| 15 | Llama 3.1 70B Instruct | 82.06 | #566 |
No result here: #4 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=helm-mmlu-human-aging · How It Works · Data refreshed daily, snapshot 2026-10-23.