I didn't like it as much as fable. The coding style was a bit different and it way overbuilt the thing I asked from it.
Opus 5 is currently #1 on Artificial Analysis Intelligence Leaderboard
21–30 of 251 posts
Re: Opus 5 is currently #1 on Artificial Analysis Intelligence Leaderboard
#22#1 in a very close race is way less useful when you have to walk on eggshells to avoid triggering censorship (“safeguards”) that either refuse or knock it down to another model. I’ve almost completely stopped using Claude (except some legacy workflows) for this reason, reliability matters more than scoring 61 instead of 57. To me Claude is the most compromised and unreliable model (between the censorship and the id c…
What are you asking that you’re so regularly running into censorship?
Re: Opus 5 is currently #1 on Artificial Analysis Intelligence Leaderboard
#23It's new, normal.
Wait until DeepSeek v5 Pro is released in less than a month and costs 1/100 to perform the same tasks.
"Not fair! They distilled Opus 5!"
Re: Opus 5 is currently #1 on Artificial Analysis Intelligence Leaderboard
#24#1 in a very close race is way less useful when you have to walk on eggshells to avoid triggering censorship (“safeguards”) that either refuse or knock it down to another model. I’ve almost completely stopped using Claude (except some legacy workflows) for this reason, reliability matters more than scoring 61 instead of 57. To me Claude is the most compromised and unreliable model (between the censorship and the id c…
Yep. I cancelled my Claude Max subscription 2 weeks ago after feeling like Anthropic was doing everything it could to fuck with my day to day. Their lead would have to become significant for me to ever go back.
Re: Opus 5 is currently #1 on Artificial Analysis Intelligence Leaderboard
#25#1 in a very close race is way less useful when you have to walk on eggshells to avoid triggering censorship (“safeguards”) that either refuse or knock it down to another model. I’ve almost completely stopped using Claude (except some legacy workflows) for this reason, reliability matters more than scoring 61 instead of 57. To me Claude is the most compromised and unreliable model (between the censorship and the id c…
What are you asking that you’re so regularly running into censorship?
If you even broach language related to biology you’ll get rerouted. I was presenting data in a grid and referred to a grid cell, Fable saw the word “cell” and safeguards kicked in
Re: Opus 5 is currently #1 on Artificial Analysis Intelligence Leaderboard
#26I didn't like it as much as fable. The coding style was a bit different and it way overbuilt the thing I asked from it.
It’s crazy that people feel confident making judgments like these when the model’s been out for only a few hours.
Re: Opus 5 is currently #1 on Artificial Analysis Intelligence Leaderboard
#27#1 in a very close race is way less useful when you have to walk on eggshells to avoid triggering censorship (“safeguards”) that either refuse or knock it down to another model. I’ve almost completely stopped using Claude (except some legacy workflows) for this reason, reliability matters more than scoring 61 instead of 57. To me Claude is the most compromised and unreliable model (between the censorship and the id c…
[flagged]
Re: Opus 5 is currently #1 on Artificial Analysis Intelligence Leaderboard
#28Earlier quoted context omitted.
What are you asking that you’re so regularly running into censorship?
If you even broach language related to biology you’ll get rerouted. I was presenting data in a grid and referred to a grid cell, Fable saw the word “cell” and safeguards kicked in
I thought we were talking about Opus 5, the model Fable now falls back to?
Re: Opus 5 is currently #1 on Artificial Analysis Intelligence Leaderboard
#29I'd be curious to see the results, especially with some models having 1.5m and 2m context sizes, if the first 75% of the context was filled with unrelated info.
Re: Opus 5 is currently #1 on Artificial Analysis Intelligence Leaderboard
#30Before getting too excited, take a look at the intelligence vs cost matrix: https://artificialanalysis.ai/models?intelligence-index-toke...
Max is lot of extra reasoning. I wonder how many fewer tasks it solves on high. I bet that costs quite a lot less.
Indeed, you can filter the graphs to see these the values for alternative reasoning settings of the models. Opus 5 High reasoning scored 59 on the index (exactly the same as GPT 5.6 Sol Max), and costs $1.06 per task (vs $1.04 Sol Max). So these seem essentially equivalent on both metrics.