pull down to refresh

126 sats \ 1 reply \ @SimpleStacker 8 Aug \ on: Stacker Saloon

I've been quite disappointed with Opus 5.... been either reverting to Opus 4.6 or going with Grok 4.5 for heavy research needs

write
compose
1 sat \ 0 replies \ @optimism 8 Aug

Grok is pretty well performing on discovery / search aggregation so for search-heavy tasks it's been great for me.

I did some experiments: let Grok make a good list of reference materials and then let either GPT or Claude work that inventory in xhigh. This went well but I lack the volume to have definitive answers on this.

GLM-5.2 has been equal/near-equal to Opus-4.6/4.7 in analytic skills for me (and often outperforming 4.8/5). Kimi K3 outperforms Opus on expensive long-running tasks.

reply