GGoogle / Gemini

AIGoogle AI Developers announced Gemini 3.7 Flash as its most intelligent workhorse model yet for coding and agents, citing higher instruction adherence, first-pass code accuracy, and high-quality agentic execution. The post shows the model building a complex 3D web game in Antigravity, covering Three.js engine logic, asset orchestration with PBR textures and Nano Banana sprite sheets, and procedural sound effects.

Why it matters: The post shows a concrete build workflow across engine logic, assets, and audio, which helps readers judge how the model handles multi-step agentic coding.

AIGoogle launches Gemini 3.7 Flash, its latest Flash model for coding and agentic workflows, with an introductory price at half the original cost of 3.6 Flash. The post reports gains from 3.5 to 3.7 Flash, including DeepSWE v1.1 rising from 37.0% to 65.3%, Code Arena Elo from 1506 to 1588, and AutomationBench from 13.4% to 30.4%.

Why it matters: The post pairs a launch with specific before-and-after benchmark gains and an introductory price, letting readers weigh capability against cost for coding and agent work.

AIGoogle introduces Gemini 3.6 Flash as its workhorse model, with better coding, knowledge work, and multimodal performance while reducing token usage. It also launches Gemini 3.5 Flash-Lite, described as the fastest and most cost-effective 3.5-class model for high-throughput applications, and 3.5 Flash Cyber, a version of 3.5 Flash fine-tuned to find and fix cybersecurity vulnerabilities.

Why it matters: The post lists three distinct models, each aimed at a different job, so readers can map which one fits coding, high-volume, or security workloads.

AIGoogle released Gemini 3.6 Flash alongside Gemini 3.5 Flash-Lite and Gemini 3.5 Flash Cyber, aimed at faster and cheaper AI agents. Jeff Dean says Gemini 3.6 Flash is much more token efficient than Gemini 3.5 Flash and shares a side-by-side video demonstration.

Why it matters: The post contrasts token use between two Flash models at the same cost, which is useful for judging efficiency gains in Gemini's agent-oriented releases.

AIGoogle's Gemini 3.5 Flash outperforms Gemini 3.1 Pro on Terminal-Bench 2.1 (76.2%), GDPval-AA (1656 Elo), and MCP Atlas (83.6%). The post also claims it is 4x faster than other frontier models, or 12x in Antigravity, and reports 83.6% on MMMU-Pro for multimodal performance.

Why it matters: The post gives specific benchmark scores against Gemini 3.1 Pro, letting readers compare coding, agentic, and multimodal results directly.

AIAt Google I/O, Google introduced Gemini 3.5 Flash, which the author says has become part of the daily research cycle. The author says a team of agents in Antigravity 2.0 recreated the original AlphaZero paper and built a playable web version from two prompts, coding the reinforcement learning pipeline in JAX/Flax and training a ResNet model via self-play on multi-TPU pods.

Why it matters: The post shows Gemini 3.5 Flash applied to an end-to-end agent task, recreating and training AlphaZero from two prompts, which indicates practical coding and research use.

AINano Banana 2, officially released as Gemini 3.1 Flash Image Preview, ranks first in Image Arena text-to-image with a score of 1279. The quoted post says it also ties for first in single-image editing at 1407 and costs $0.067 per image, about half the price of Nano Banana Pro.

Why it matters: The quoted leaderboard figures and per-image price give concrete reference points for comparing this image model against Nano Banana Pro and GPT-Image-1.5.

AIGoogle researchers used the Aletheia agent, powered by Gemini 3 Deep Think, to attempt 10 FirstProof challenge problems without modification. The agent operated fully autonomously and solved 6 of the 10 problems, according to the post, with methodology and expert evaluations described in the linked arXiv paper.

Why it matters: The post gives the autonomous setup and expert-evaluated results for an AI agent on FirstProof math problems, useful for judging how far such systems go on research-level math.

AIQuoc Le announced a case study using Gemini to systematically evaluate 700 conjectures labeled open in the Erdős Problems database. The team addressed 13 problems, finding 5 novel autonomous solutions and identifying 8 existing solutions missed by previous literature.

Why it matters: The case study shows how a systematic AI sweep found new solutions and missed prior literature across 700 open Erdős conjectures, offering a concrete look at AI-assisted math research.