HELM VHELM - Mme: leaderboard
The "Mme" subtask of HELM VHELM. Stanford HELM's VHELM project, the holistic evaluation of vision-language models: image-grounded question answering, OCR, chart and diagram reading, spatial reasoning, robustness, bias, fairness and toxicity scenarios scored under one ha...
Metric: PEM. Source: crfm.stanford.edu. Saturation forecast: Estimated already saturated. 48 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro (Preview 03-25) | 92.7 | #124 |
| 2 | GPT-4.1 (2025-04-14) | 91.87 | #250 |
| 3 | GPT-4o (2024-08-06) | 91.2 | #335 |
| 4 | Gemini 1.5 Pro (002) | 90.93 | #350 |
| 5 | Claude 3.5 Sonnet (20241022) | 90.92 | #291 |
| 6 | Gemini 2.0 Pro (Preview 02-05) | 90.66 | #305 |
| 7 | GPT-4o (2024-05-13) | 90.39 | #326 |
| 8 | Gemini 1.5 Flash (002) | 89.88 | #585 |
| 9 | GPT-4o (2024-11-20) | 89.43 | #378 |
| 10 | GPT-4.5 | 88.57 | #276 |
| 11 | Claude 3.5 Sonnet (20240620) | 87.53 | #298 |
| 12 | Llama 4 Scout Instruct | 87.17 | #542 |
| 13 | Gemini 2.0 Flash | 87.12 | #344 |
| 14 | GPT-4.1 Mini | 85.46 | #351 |
| 15 | GPT-4 Turbo | 84.26 | #406 |
No result here: #4 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=helm-vhelm-mme · How It Works · Data refreshed daily, snapshot 2026-10-23.