Gemini 3.7 Flash Tested: Major Boosts in Coding and Reasoning at Half the Cost
petrusenko_max · x · 2026-08-14
The author compares the performance of Gemini 3.7 Flash against version 3.6. Data shows significant improvements in coding accuracy (FrontierCode benchmark rose from 34.4% to 43.6%) and knowledge work reasoning (GDP.pdf benchmark increased from 22% to 34%).
Additionally, the new model generates more complete web applications with fewer prompts, while cutting the cost per million tokens by 50%, achieving a dual breakthrough in performance and cost-efficiency.
More from Models
- GPT-5.6 Luna Beats Gemini 3.7 Flash in Score at One-Third the Cost — haider1 · 2026-08-14
- Gemini 3.7 Generates a 3D Rolex in Pure Three.js for Just $0.038 — rohanpaul_ai · 2026-08-14
- Price Hike on Open Weights Models Sparks Controversy in AI Community — teortaxesTex · 2026-08-14
- ChatGPT GitHub Connector Hits False Positives with Safety Blocks — Phoxerity · 2026-08-14
- Code Leak: Gemini CLI Adds Claude Sonnet 4.5 and Opus 4.8 Models — RussellZager · 2026-08-14
- LLM Price Wars: DeepSeek Hikes 1114%, Grok and Gemini Slash Prices — kimmonismus · 2026-08-14