Great to see MiniCPM-V-4.7-35B-A3B being tested in real agent workflows. 👀
Strong tool use, long context handling, and agent loops are exactly where efficient models need to prove themselves.
OpenBMB's MiniCPM-V-4.7-35B-A3B tested in real agent workflows
AIOpenBMB says MiniCPM-V-4.7-35B-A3B is being tested in real agent workflows, where tool use, long context handling and agent loops test efficient models. Paul Gug reports the model beat 35B MoE models he would normally use in his own agent benchmarks, with a perfect score on Lite Agent testing (A1) and strong results on PA4, a complex agent loop with long context and tool calls.
@OpenBMB
I appreciated @OpenBMB giving a few of us an early look at these new models. They are the real deal. When I put MiniCPM-V 4.7 35B A3B through my own personal agent benchmarking (see comments for more info on what I test and why), it outperforms 35B MoE incumbents that one would normally reach for. Lite Agent testing (A1) was a perfect result, and PA4 (bringing a complex agent loop workflow together with lots of context and tool calls) was surprisingly strong. This is even before looking at the new vision and other capabilities, but as a life admin 'brain' - it's quite stellar.
Source details
OpenBMB · x.comPublished · added here
Original title: Great to see MiniCPM-V-4.7-35B-A3B being tested in real agent workflows. 👀