gemini-4VIDEO
新基准测试:nanoannot-1 击败 Gemini 4 Argon
团队发布 MicroPlanBench 与 MicroAnnotationBench 两个新基准,称自研 nanoannot-1 在长视频标注任务上以 1/10 成本胜过 Gemini 4 Argon。
Bercan
@bercankilic15 天前收录原推发布于 2026.10.20
Bercan @bercankilic原推发布于 2026.10.20
Today we are releasing two new benchmarks: MicroPlanBench (next-action prediction): GPT-6 Astra and GPT-6.1 Sol lead. Sol costs 1/5 as much. MicroAnnotationBench (labels + timing on long real-world clips): our nanoannot-1 beats Gemini 4 Argon, at 1/10 the cost.
x.com/bercankilic/status/2112316584534388884采集于 2026.10.20 09:56