Tabbit
ResourcesBlogModels
Tabbit LogoTabbit

Tabbit — The AI Browser that Works for You

Topics

  • Best Browsers 2026: Rankings and Top Lists
  • AI Browser Guides and Resources
  • Browser Comparisons: Head-to-Head Guides
  • Browser Reviews and Explainers
  • Browser Alternatives
  • Browser Directory: Guides by Browser
  • Agentic Browser Resources
  • Browser Downloads and Install Guides
  • Browser Productivity Resources
  • SillyTavern Model Guides and Presets

Popular Guides

  • Best Browsers 2026: Top 10 Ranked & Compared
  • Best Free AI Browsers 2026: Plans & Prices Compared
  • Rabbit Browser: What It Is & Why Tabbit Is Better
  • Firefox vs Chrome 2026: Privacy, RAM & Speed Compared
  • Best Lightweight Browsers 2026: 7 Tested for RAM & Speed
  • AI Browser List 2026: 10 Browsers Compared
  • Neobrowser: Norton Neo, Download & Alternatives
  • Edge vs Chrome 2026: Speed, RAM & Battery Tested
  • Best Internet Browser for Android 2026
  • Best AI Browser 2026: Top 9 Tested & Ranked

Events

  • Tabbit Skill Competition
  • KPOP SBTI Fandom Personality Test
  • Tabbit Campus Creator Program
  • fifi's Picks: AI Skills for Research Papers
  • User Survey

About

  • Tabbit Blog
  • Press & Media
Review
OfficialGemini 4 Neon

Science, coding, and multimodal benchmarks in the Gemini 4 Neon model card

Original source

Google DeepMind

AuthorUnspecified

Source date2026-11-18

Tabbit curation2026-11-18

Read original

One-sentence takeaway

Google DeepMind reports that Neon scored 84.0% on RiemannBench and 39.0% and 12.8% on SWE-sweep in two different agent environments, so consider both the reasoning tier and the agent environment when choosing a model.

Use cases

  • Tasks these results can help assess: Mathematical and scientific reasoning, agent tasks in codebases, chart and video understanding, and graph traversal in long contexts.

  • What requires separate evaluation: Success rates on real-world business tasks, factual accuracy, latency, cost, and performance in other clients.

  • Applicable model version: Gemini 4 Neon, adapted from Gemini 4 Carbon. The evaluation materials do not specify the API model revision for each benchmark.

  • Test environment or client: The methodology uses the Gemini API by default and documents the agent environment, tool configuration, or source of public scores for each benchmark.

  • Reasoning tier and parameters: The methodology says it uses the highest thinking setting by default, without naming the default tier. FrontierCode 2.0 explicitly uses High. The materials do not specify sampling parameters such as temperature.

Evaluation method

The official results are current as of November 2026. By default, the methodology reports the single-attempt pass rate (pass@1), with majority voting and parallel inference disabled for single-attempt evaluations. Some small benchmarks average results across multiple runs to reduce variability. The model card combines DeepMind's own evaluations with external benchmark scores. The table gives the setup for each result. Official evaluation methodology PDF

Key results

TaskBenchmarkNeonSource and configuration
MathRiemannBench84.0%Benchmark's official leaderboard
ScienceTerminal-Bench-Science 0.170.5%Evaluated by DeepMind using mini-swe-agent vision, with the reward averaged over 5 runs per question
Agentic codingCursorBench 4.165.4%Score reported by Cursor
Agentic codingFrontierCode 2.046.2%Benchmark's official leaderboard, with Neon using High
Agentic codingSWE-sweep39.0% / 12.8%Evaluated by DeepMind using Antigravity CLI 1.5.9 and mini-swe-agent vision, respectively, with scores weighted by subtask
Chart understandingChartography73.5%Evaluated by DeepMind using Surge's public leaderboard methodology, with tools disabled
Video understandingLVBench89.0%Evaluated by DeepMind with tools disabled, with Gemini sampling 1 frame per second at low resolution
Long contextGraphWalks95.2%Evaluated by DeepMind on 200 questions with contexts ranging from 256k to 1M tokens, using F1 for breadth-first search

Raw data

The scores come from the model card's Evaluation table, and the configurations come from the Methodology and Additional Details sections of the companion PDF. The model card specifies a combined input and output context limit of 1M tokens. The default synchronous output limit is 64K tokens. Long decoding in the background can output up to 1M tokens, subject to the shared context limit. Model card · Official evaluation methodology PDF

Conclusions and limitations

The two SWE-sweep scores each correspond to a specific agent environment. The 95.2% GraphWalks score is an F1 score for graph traversal over the specified range of context lengths. Accuracy on real-world long-document question answering needs to be measured separately. The benchmarks define their scores differently, so each percentage is meaningful only within its task and scoring method.

The model card notes that Neon can hallucinate. Its knowledge cutoff is March 2026, and its knowledge in some areas may be older. The science, multimodal, and long-context results apply to their respective test sets. Fact-checking still requires consulting primary sources.

Reproduction notes

To verify the results, use the November 2026 results table in the model card and check the PDF for each benchmark's run environment, tools, and scoring method. If rerunning the evaluations, record the model revision, thinking setting, benchmark version, agent environment, and tool permissions. The public materials let you verify aggregate scores and disclosed configurations. They do not provide per-question results, complete invocation parameters, or confidence intervals for every benchmark.

Curated by Tabbit

This is a third-party source navigator. Model versions, test environments, and personal experience vary; consult the original source.

Gemini 4 Neon

Use and compare models in Tabbit

Gemini 4 Neon

Related reviews

MediaArtificial Analysis2026-11-18

Gemini 4 Neon benchmark scores, latency, and cost across four reasoning tiers

CommunityX2026-11-19

Gemini 4 Neon (High) ranks second on Agent Arena's real-world task leaderboard

MediaZapier

Gemini 4 Neon pass rates and costs across four reasoning tiers on Zapier AutomationBench

MediaVals AI2026-11-18

Gemini 4 Neon scores, costs, and runtimes on Vals Index 2.2

Gemini 4 Neon

Related showcases & prompts

OfficialGoogle AI Studio / Gemini API

Gemini 4 Neon model ID and Gemini API specifications

OfficialGoogle AI Studio / Gemini Developer API

Estimating Gemini 4 Neon API costs by inference mode

OfficialOpenRouter

Calling Gemini 4 Neon through OpenRouter and choosing an upstream endpoint

MediaGoogle Cloud Gemini Enterprise Agent Platform2026-11-18

Regions and inference settings for Gemini 4 Neon on Google Cloud