Ok so if you look here for example:
It says at the end of the description,
LunarLander-v2 defines "solving" as getting average reward of 200 over 100 consecutive trials.
Thus if you take the last 100 trials and then average that number you should get your "average" over 100 trials, since you're doing -100 it will always grab the last 100, every episode you run, so in the early stages you don't actually have 100 episodes, so it might spit out a warning but I wouldn't worry about it.
I was using it as termination decision, so stop running episodes when I hit a 200 average, but you gotta make sure that you run the minimum 200, so if you're "re-training" (meaning you already have good weights) make sure you run 100 runs before letting that termination occur.
if (above average) > 200 and episode_count > 100: