LLM2014 Vision 2025-07: leaderboard
LLM2014 monthly vision benchmark for 2025-07, reporting multimodal visual-reasoning performance on the source score scale.
Metric: Median Score. Source: raw.githubusercontent.com. Saturation forecast: Estimated already saturated. 16 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 61.8 | #152 |
| 2 | O4 Mini (High) | 53.4 | #180 (O4 Mini) |
| 3 | Claude Sonnet 4 | 41.21 | #199 |
| 4 | Claude Sonnet 4 (Thinking) | 38.83 | #199 (Claude Sonnet 4) |
| 5 | SenseNova V6 Reasoner | 37.38 | #306 |
| 6 | Seed-1.6 | 35.32 | #265 |
| 7 | MiniMax-Text-01 | 23.38 | #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-2025-07 · How It Works · Data refreshed daily, snapshot 2026-10-20.