AI Briefing#model-benchmark
The latest AI and developer news about #model-benchmark, with the original source and a short summary.
The latest AI and developer news about #model-benchmark, with the original source and a short summary.
The 1.6T parameter model achieves 88.4 on Terminal Bench v2.1 and 91.9 on BrowseComp, outperforming LongCat-2.0 and approaching frontier models like Claude-Opus-5.
According to a Mozilla report, the performance gap between open and closed models has narrowed to an average of about 4 months, with competition shifting from the models themselves to harnesses.
Qwen has released the Qwen3.8 open model with a total size of 2.4T and 95B active parameters.
On 111 SWE problems, Fable 5 recorded the highest resolve rate at 64.5%.
GPT-5.5 topped the intelligence index on Artificial Analysis, but it also ranked among the most expensive.