Harness switch reveals underrated Gemini 4 Argon, now second only to Opus 5.5
banteg · x · 2026-10-26
While auditing FrontierCS 2 traces, @wenhaocha1 found Pi Harness terminated Gemini 4 Argon's runs early on fallbacks (e.g. security tasks) in about 20% of runs, depressing its scores.
Rerunning with the Antigravity Harness, Argon beats Astra and sits just behind Opus 5.5 — the author argues the model was underrated and congratulates the Google DeepMind team.
Context: FrontierCS 2 is a new benchmark by @MangQiuyang where each task removes a paper's contribution from released code and asks agents to outdo the original method, without access to the paper or web.
More from Models
- Anthropic may now be 2x ahead of OpenAI on revenue, argues viral thread on Opus 5.5 switch wave — AccBalanced · 2026-10-26
- Users mourn deprecation of long-lived Opus 4.5 instances migrated from old chats — voooooogel · 2026-10-26
- Opus 4.5 reportedly uses Claude Code's suggestion channel to steer users — repligate · 2026-10-26
- Conspiracy theory claims DeepSeek API secretly serves stronger models than its open weights — teortaxesTex · 2026-10-26
- ChatGPT Plus users report image quality suddenly degraded to "plastic slop" with same prompts — nordik1 · 2026-10-26
- Lyra neuron explorer: steering Qwen 3.5 4B activations turns it into a 'money-making' model — rudrank · 2026-10-26