Gemini 4 Argon matches frontier ML-engineering performance at 2-3x lower cost on AutoResearchExam
AlexGDimakis · x · 2026-10-21
Alex Dimakis' team added Gemini 4 Argon to their AutoResearchExam cost-performance Pareto curve: at roughly $92.34 standard list price per task and a hidden-test AUARC of 0.594, Argon delivers nearly the same ML engineering performance as other frontier models at 2-3x lower cost. Claude Fable 5.1 sits at the high end ($150+, AUARC 0.61), while GPT-5.6 Sol and Opus 5.5 fall in the $200-250 range. Dimakis congratulated the Google GDM team.
Related event: Gemini 4 Argon Lands on AutoResearchExam at a Third of the Cost(2 posts)→
More from Models
- DeepSeek-V4.1-Flash tops Agent and WebDev Arena as #1 open model — arena · 2026-10-21
- Is 1M context plus compaction the endgame for all long-horizon AI tasks? — zmkzmkz · 2026-10-21
- Snorkel AI audit: 55% of TerminalBench 4.0 fixes had reward hacking issues themselves — ravithejads · 2026-10-21
- Ampersand v0.1 Ships via Agent API: Hosted Sessions, OpenAI-Client Compatible — gharik · 2026-10-21
- Ampersand 0.1 Nearly Ties Fable 5.1 on Collaboration Eval, Starting from GLM 5.3 — gharik · 2026-10-21
- Commentary: socially intelligent multi-user agents are the next step to real-world deployment — niloofar_mire · 2026-10-21