c/machinelearning42d agoFor a better means of comparison, you get over 2.5X the Opus 5.5 tokens on Claude's Max 20x plan than Sol 6.1 on Pro 20x https://x.com/synthwavedd/status/2107208147152544057/photo/1@erikmackinnon · X@synthwavedd Equivalent AA score at 51 gpt-6.1-sol-xhigh opus-5.5-medium opus takes 44% more tokens to achieve it so any more tokens past +44% over OpenAI subs should be considered more at $200, the diff is 180% in favor of anthropic https://x.com/erikmackinnon/status/2107215420520636891/photo/1View conversation
@synthwavedd Equivalent AA score at 51
gpt-6.1-sol-xhigh opus-5.5-medium
opus takes 44% more tokens to achieve it
so any more tokens past +44% over OpenAI subs should be considered more
at $200, the diff is 180% in favor of anthropic https://x.com/erikmackinnon/status/2107215420520636891/photo/1