Projecting something that is already out is an epistemic crime.
[3 hidden]5 mins ago
I guess what I really want to know is how Gemini 4 Neon w/Antigravity compares with Opus 5.5/Claude Code. I'm not really into using LLMs in a particularly advanced way, I just use CC like 99% of the time when I need to write something, and then maybe Codex to second guess it.
But that's about as complicated as I get. I have recently tried to use Copilot because that is what work wants us to use, and even with Opus 5.5 it is noticeably inferior to CC on the same model. Wild. So clearly the harness matters.
[3 hidden]5 mins ago
The models can be very optimized for the harness, Clem (of Hugging Face) just recently released a Qwen3.8 model that used RL training on the harness and it got some pretty significant gains in the benchmarks.
Totally possible for your use case, though the analyses I’ve done on harness model interactions show it’s actually not that important for benchmark performance. https://micjm.com/blog/on-model-harness-interactions/
For what it’s worth, the linked article data (Agent Duel data) is all run on OpenCode. I’m curious if people would prefer we run each model in its native harness (at the expense of user experience because it’ll be buggy).
[3 hidden]5 mins ago
We had CC for a while and now have to use GHCP. As such I haven't used CC in like 6 months but around the time I switched I felt like GHCP CLI had pretty much caught up. Curious to hear what you feel are the gaps? Are you using the cli versions of both?
[3 hidden]5 mins ago
Also last I checked there was no clear flag to turn off training in paid plan of Antigravity. So if you care about that looks like Google doesn’t want you as their customer.
[3 hidden]5 mins ago
Fun analysis. I guess it’s not surprising to see the need for speed™ as an important factor, but who is using Fable for run of the mill coding work? It’s too pricey!
[3 hidden]5 mins ago
I used it to write something last night that was intricate enough that Opus would have involved a lot more rework. Subscription discount though.
[3 hidden]5 mins ago
Yeah, check out DeepSeek performance on the leaderboard (http://agentduel.com/leaderboard). It wins ~half the time because it’s lightning fast and good enough.
[3 hidden]5 mins ago
I'm pretty impressed so far, this is the first google model I've used that feels good for coding
[3 hidden]5 mins ago
Looks like a good bunch of speculation in there but no bad news to be found. Just as good but cheaper? Sign me up.
For this model, I mean. And not the Anthropic IPO.
[3 hidden]5 mins ago
Lots of speculation, yes.
Just as good but cheaper comes from the benchmark performance. Also faster from openrouter. The opus 5.5 parity projection is an internal model based on those assumptions from the Agent Duel team.
But that's about as complicated as I get. I have recently tried to use Copilot because that is what work wants us to use, and even with Opus 5.5 it is noticeably inferior to CC on the same model. Wild. So clearly the harness matters.
- SWE-bench Pro (hard 51): 39.2% → 64.7%
- Terminal-Bench 2.1: 39.5% → 55.8%
https://huggingface.co/harness-hub/Qwen3.8-27B-pi-adapted
For what it’s worth, the linked article data (Agent Duel data) is all run on OpenCode. I’m curious if people would prefer we run each model in its native harness (at the expense of user experience because it’ll be buggy).
For this model, I mean. And not the Anthropic IPO.
Just as good but cheaper comes from the benchmark performance. Also faster from openrouter. The opus 5.5 parity projection is an internal model based on those assumptions from the Agent Duel team.