LLM2014 Vision 2025-05: leaderboard
LLM2014 monthly vision benchmark for 2025-05, reporting multimodal visual-reasoning performance on the source score scale.
Metric: Median Score. Source: raw.githubusercontent.com. Saturation forecast: Estimated already saturated. 15 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro (Preview 05-06) | 61.94 | #147 |
| 2 | O4 Mini (High) | 49.41 | #180 (O4 Mini) |
| 3 | Claude 3.7 Sonnet (Thinking) | 43.43 | #249 (Claude 3.7 Sonnet) |
| 4 | SenseNova V6 Reasoner | 36.71 | #306 |
| 5 | MiniMax-Text-01 | 24.83 | #513 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=llm2014-vision-2025-05 · How It Works · Data refreshed daily, snapshot 2026-10-20.