CAGE - Association (Text-Only Probe): leaderboard

Metric: Judge score (0-10), mean of GPT-4o and Claude 3.5 Sonnet ratings of accuracy, relevance and logical consistency against GPT-4o-generated reference answers; level-1 association (what is observed) questions, 3 per image on 500 COCO test images; free-text answer without a causal chain (Text-Only Probe); blank responses score 0. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 8 models tracked.

Top models

#ModelScore
1CogVLM2-19B8.38
2Qwen-VL-Chat8.23
3InternVL2-76B7.97
4LLaVA-NeXT-13B7.95
5LLaVA-CoT7.92
6MiniGPT-4-Vicuna-13B7.1
7mPLUG-Owl26.8
8LLaVA-RLHF-13B5.12

Interactive version: theaggregate.ai/benchmark?slug=cage-association-text-only-probe · How It Works · Data refreshed daily, snapshot 2026-09-26.