Assuming the performance problem is the ME3400 being the GRE tunnel end-point, GRE effective performace of the head of the tunnel might be impacted by packet fragmentation.
I've never worked with the ME3400, elimination of fragmentation, if there's any might not help, but perhaps worth checking. Also, L3 switches are a bit of a special case because of their hardware, but within the software routers, IOS version upgrades sometimes can improve performance of some traffic flows. Perhaps, if not running the latest software for your ME3400, you might investigate whether an upgrade might be of benefit too.
We are pleased to announce availability of Beta software for 16.6.3. 16.6.3 will be the second rebuild on the 16.6 release train targeted towards Catalyst 9500/9400/9300/3850/3650 switching platforms. We are looking for early feedback from custome...