Naeem
404 posts
Bonus, your competitors are in absolute dumpster fire. like ant and google.
x.com/themarginguy/s…
Margins@themarginguy
We are seeing a sustained statistically significant degradation in Claude Code with Opus 4.7 since last Friday May 22nd at marginlab.ai/trackers/claud…
English
I’ll trust any benchmark where Google’s models perform poorly.
Serena Ge (Datacurve)@serenaa_ge
Today we’re releasing DeepSWE, a new standard for agentic coding benchmarks. On public leaderboards, top models often look relatively close in capability. DeepSWE shows where they actually diverge, reflecting the realistic experience of developers in their day-to-day work.
English
Do you prefer Composer 2.5 now, or do you still reach for Opus for UI-heavy work?
English
Not surprising for people using these models
Serena Ge (Datacurve)@serenaa_ge
Today we’re releasing DeepSWE, a new standard for agentic coding benchmarks. On public leaderboards, top models often look relatively close in capability. DeepSWE shows where they actually diverge, reflecting the realistic experience of developers in their day-to-day work.
English
the rankings are very good, but now that it has been released it will be fucked into oblivion
Serena Ge (Datacurve)@serenaa_ge
Today we’re releasing DeepSWE, a new standard for agentic coding benchmarks. On public leaderboards, top models often look relatively close in capability. DeepSWE shows where they actually diverge, reflecting the realistic experience of developers in their day-to-day work.
English
Composer 2.5 outperforms all open source models and clearly beats its base model Kimi 2.5 as well as Kimi 2.6. It is roughly on par and slightly ahead of Gemini 3.1 Pro
We still see a large gap between models from Anthropic / OpenAI and other labs
Proximal@ProximalHQ
Composer 2.5 is ranked #5 on FrontierSWE The model is broadly on par with Gemini 3.1 Pro, with a slight edge in our evaluation, and it beats all open source models. We still observe a significant performance gap between Composer and models from Anthropic and OpenAI
English
Today we’re releasing DeepSWE, a new standard for agentic coding benchmarks.
On public leaderboards, top models often look relatively close in capability. DeepSWE shows where they actually diverge, reflecting the realistic experience of developers in their day-to-day work.
English
