HELM VHELM - Math Vista - Daily Life (Multiple Choice): leaderboard
VHELM (Stanford CRFM HELM for vision-language models, run v2.1.2) MathVista items at grade level daily life in multiple choice format: mathematical reasoning over plots, charts, diagrams and photos; 160 questions, exact match. Percent correct, 0-100, higher is better.
Metric: Exact Match (%). 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) | 81.88 | #126 |
| 2 | O4 Mini (2025-04-16) | 78.75 | #183 |
| 3 | O3 (2025-04-16) | 78.75 | #125 |
| 4 | GPT-4.5 | 76.88 | #278 |
| 5 | GPT-4.1 (2025-04-14) | 74.38 | #257 |
| 6 | O1 (2024-12-17) | 73.75 | #157 |
| 7 | GPT-4o (2024-05-13) | 70.62 | #337 |
| 8 | GPT-4o (2024-08-06) | 69.38 | #343 |
| 9 | Gemini 2.0 Flash (Preview) | 69.38 | #376 |
| 10 | Gemini 2.0 Flash | 68.75 | #351 |
| 11 | Gemini 2.0 Pro (Preview 02-05) | 66.88 | #318 |
| 12 | Claude 3.5 Sonnet (20241022) | 66.25 | #302 |
| 13 | GPT-4.1 Mini | 65.62 | #363 |
| 14 | GPT-4o (2024-11-20) | 65.62 | #392 |
| 15 | Llama 4 Maverick Instruct FP8 | 65 | #424 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=helm-vhelm-math-vista-daily-life-multiple-choice · How It Works · Data refreshed daily, snapshot 2026-11-05.