KOFFVQA - Recognition: leaderboard
KOFFVQA subscore for visual recognition questions over objects and scenes.
Metric: Score (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 82 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | O1 (2024-12-17) | 100 | #149 |
| 2 | Gemini 2.5 Flash (Preview 04-17) | 100 | #237 |
| 3 | Gemma 3 27B (IT) | 90 | #523 |
| 4 | GPT-4.1 Mini | 90 | #355 |
| 5 | GPT-4.1 | 90 | #248 |
| 6 | Claude 3.5 Sonnet (20241022) | 90 | #291 |
| 7 | Gemini 1.5 Pro (002) | 90 | #349 |
| 8 | Gemini 1.5 Flash (002) | 90 | #583 |
| 9 | Gemini 2.5 Pro (Preview 03-25) | 90 | #123 |
| 10 | GPT-4 Turbo | 90 | #404 |
| 11 | O4 Mini (2025-04-16) | 90 | #179 |
| 12 | GPT-4o (2024-11-20) | 90 | #381 |
| 13 | Qwen 2.5 VL 72B Instruct | 90 | #377 |
| 14 | Gemini 2.5 Pro (Preview 05-06) | 90 | #147 |
| 15 | Gemini 2.0 Flash Lite (001) | 90 | #544 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=koffvqa-recognition · How It Works · Data refreshed daily, snapshot 2026-10-20.