Ant Group’s Ling-3.0-flash-VL scores 25 on Intelligence Index, Artificial Analysis says

Artificial Analysis reports that Ant Group’s Ling-3.0-flash-VL scores 25 on its Intelligence Index. Among models it describes as similar in total size, Qwen3.5 122B A10B (Reasoning) scores 16 and Mistral Medium 3.5 (high) scores 15. The evaluator reports a lower hallucination rate than comparable models but limited factual recall, with 14% accuracy and a 22% hallucination rate on AA-Omniscience. It also flags difficulty with demanding tasks: the model scores 16% on AutomationBench-AA, which tests workflows across business apps while respecting guardrails, and 0% on the harder terminal-use test Terminal-Bench v4.0.