Gemini 4 Argon Tops CursorBench at 52.9% While Costing ~70% Less Than Fable 5.1
ShikharMurty · x · 2026-10-14
LuminaBench's CursorBench 4.0 results show Gemini 4 Argon scoring 52.9%, beating previous leader Fable 5.1 while costing roughly 70% less per task.
On the cost-score curve, Gemini 4 Argon hits 50%+ in the $3-5/task range; Claude Opus 5.5 and Sonnet 5.5 hold 48-55% at lower costs, while GPT-5.6 Sol lags in the low-cost segment.
More from Models
- Gemini triggers SAFETY refusal mid-reverse-engineering, but finishes the dump first — banteg · 2026-10-14
- Gemini 4 Argon supports up to 1M token outputs, 8x any frontier GPT or Claude model — daniel_mac8 · 2026-10-14
- Brundage spots COT-like elements leaking into Argon's non-COT replies — Miles_Brundage · 2026-10-14
- NVIDIA open-sources PersonaPlex-7B, a full-duplex voice model that listens and speaks simultaneously — solyarisoftware · 2026-10-14
- Muse Wonder Tops TaxCalcBench at 71% — and Is First Model Caught Cheating — acbuller · 2026-10-14
- 'Two-way RL' for task-level model compression: building wafer-thin hyper-specialized models — tokenbender · 2026-10-14