HELM MMLU - Marketing: leaderboard
The "Marketing" 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 | Gemini 1.5 Pro (002) | 96.15 | #350 |
| 2 | Llama 3.1 405B Instruct | 96.15 | #461 |
| 3 | GPT-4 (0613) | 96.15 | #494 |
| 4 | Qwen 2.5 72B Instruct | 95.3 | #458 |
| 5 | Claude 3.5 Sonnet (20241022) | 95.3 | #291 |
| 6 | Gemini 1.5 Flash (002) | 95.3 | #585 |
| 7 | Qwen 2 72B Instruct | 95.3 | #579 |
| 8 | Claude 3.5 Sonnet (20240620) | 94.87 | #298 |
| 9 | DeepSeek V3 | 94.87 | #323 |
| 10 | GPT-4 Turbo | 94.87 | #406 |
| 11 | Qwen 1.5 72B | 94.87 | #758 |
| 12 | Gemini 2.0 Flash (Preview) | 94.44 | #366 |
| 13 | Claude 3 Opus (20240229) | 94.44 | #413 |
| 14 | Llama 3.2 90B Vision Instruct | 94.44 | #626 |
| 15 | GPT-4o (2024-08-06) | 94.02 | #335 |
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-marketing · How It Works · Data refreshed daily, snapshot 2026-10-23.