GDPval-MM: leaderboard
Multimodal variant of GDPval evaluating models on economically valuable tasks across industries requiring processing and generating documents, slides, diagrams, spreadsheets, images, and other professional deliverables.
Metric: Wins + ties (imported). Source: openai.com. Source: benchmarklist.com. Saturation forecast: Around April 2027. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.2 | 70.9 | #110 |
| 2 | Claude Opus 4.5 | 59.6 | #83 |
| 3 | Gemini 3 Pro | 53.5 | #80 |
| 4 | Claude Sonnet 4.5 | 50.3 | #142 |
| 5 | Claude Opus 4.1 | 47.6 | #140 |
| 6 | GPT-5 | 38 | #98 |
| 7 | O3 | 34.1 | #124 |
| 8 | O4 Mini (High) | 27.8 | #180 (O4 Mini) |
| 9 | Gemini 2.5 Pro | 25.5 | #152 |
| 10 | Grok 4 | 24.3 | #181 |
| 11 | GPT-4o | 12.3 | #343 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=gdpval-mm · How It Works · Data refreshed daily, snapshot 2026-10-20.