Terminal-Bench 2.1
Cline harness lifts NVIDIA Nemotron 3.5 Super VL to 61.8% on Terminal-Bench 2.1
Cline reports that NVIDIA's Nemotron 3.5 Super VL scored 61.8% on Terminal-Bench 2.1 when run through the Cline agent harness with thinking mode turned off. According to…
Meta's Muse Spark Open Weights Now Available on Modal Auto Endpoints
Meta has released weights for Muse Spark Open, a model built for agentic coding and long-horizon tasks, and it is now available on Modal Auto Endpoints. Modal says the…
DeepSeek V4.1 Flash Arrives on Novita AI With Image Input and Stronger Coding
Novita AI now offers DeepSeek V4.1 Flash as a serverless API, bringing image input and higher agentic coding scores than DeepSeek V4 Flash at the same 1M-token context.…