# Gemini 4 Carbon Benchmark Scores & Performance > Gemini 4 Carbon by Google scores 88.42/100 overall, ranking #1 out of 1002 AI models. Canonical page: https://benchlm.ai/models/gemini-4-carbon Last updated: October 28, 2026 ## Model Details | Property | Value | |----------|-------| | Creator | Google | | Source Type | Proprietary | | Reasoning Type | Reasoning | | Context Window | Coming soon | | Official model card | [Google Gemini 4 Carbon evaluation methodology](https://deepmind.google/models/evals-methodology/gemini-4-carbon) | | Overall Score | 88.42/100 | | Overall Rank | #1 of 1002 | ## Family & Coverage - Family: Gemini 4 - Variant: base - Benchmarks covered: 23 of 717 - Sibling models: [Gemini 4 Argon](/models/gemini-4-argon) - Related earlier model: [Gemini 4 Argon](/models/gemini-4-argon) - Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative. ## Agentic Benchmarks | Benchmark | Score | Source | |-----------|-------|--------| | [AutomationBench](/benchmarks/automationbench) | 53.9% | [Google: Gemini 4 Carbon evaluation methodology](https://deepmind.google/models/evals-methodology/gemini-4-carbon) | | [AA Terminal-Bench 4.0](/benchmarks/terminal-bench-4) | 65.2% | [Google: Gemini 4 Carbon evaluation methodology](https://deepmind.google/models/evals-methodology/gemini-4-carbon) | | [OSWorld 2.1 Offline](/benchmarks/osworld-2-1-offline) | 81.5% | [Google: Gemini 4 Carbon evaluation methodology](https://deepmind.google/models/evals-methodology/gemini-4-carbon) | | [CWE-bench v1](/benchmarks/cwe-bench-v1) | 71.0% | [Collinear: CWE-bench v1 leaderboard](https://cwe-bench.com/) | | [ExploitGym](/benchmarks/exploitgym) | 53.5% | [Google: Gemini 4 Carbon evaluation methodology](https://deepmind.google/models/evals-methodology/gemini-4-carbon) | | [AA Briefcase](/benchmarks/aabriefcaseelo) | 1609 | [Artificial Analysis: aa-briefcase leaderboard](https://artificialanalysis.ai/evaluations/aa-briefcase) | | [AA AutomationBench](/benchmarks/aaautomationbench) | 77.8% | [Artificial Analysis: automationbench-aa leaderboard](https://artificialanalysis.ai/evaluations/automationbench-aa) | | [GDPval-AA](/benchmarks/gdpvalaa) | 1733 | [Artificial Analysis: gdpval-aa leaderboard](https://artificialanalysis.ai/evaluations/gdpval-aa) | | [GDP.pdf](/benchmarks/aagdppdf) | 28.4% | [Artificial Analysis: gdp-pdf leaderboard](https://artificialanalysis.ai/evaluations/gdp-pdf) | ## Coding Benchmarks | Benchmark | Score | Source | |-----------|-------|--------| | [FrontierSWE v2](/benchmarks/frontierswev2) | 61.2% | [Proximal: FrontierSWE v2 leaderboard](https://www.frontierswe.com/) | | [AA-SciCode](/benchmarks/aascicode) | 64.2% | [Artificial Analysis: scicode leaderboard](https://artificialanalysis.ai/evaluations/scicode) | ## Multimodal & Grounded Benchmarks | Benchmark | Score | Source | |-----------|-------|--------| | [Chartography (no tools)](/benchmarks/chartography) | 72.5% | [Google: Gemini 4 Carbon evaluation methodology](https://deepmind.google/models/evals-methodology/gemini-4-carbon) | | [Blueprint-Bench 2](/benchmarks/blueprintbench2) | 58.6% | [Google: Gemini 4 Carbon evaluation methodology](https://deepmind.google/models/evals-methodology/gemini-4-carbon) | ## Reasoning Benchmarks | Benchmark | Score | Source | |-----------|-------|--------| | [GraphWalks BFS 256K–1M](/benchmarks/graphwalks-bfs-256k-1m) | 96.2% | [Google: Gemini 4 Carbon evaluation methodology](https://deepmind.google/models/evals-methodology/gemini-4-carbon) | | [AA-LCR](/benchmarks/lcr) | 79.3% | [Artificial Analysis: artificial-analysis-long-context-reasoning leaderboard](https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning) | | [CritPt](/benchmarks/critpt) | 36.0% | [Artificial Analysis: critpt leaderboard](https://artificialanalysis.ai/evaluations/critpt) | ## Knowledge Benchmarks | Benchmark | Score | Source | |-----------|-------|--------| | [Artificial Analysis Intelligence Index](/benchmarks/artificialanalysis) | 59.4% | [Artificial Analysis: artificial-analysis-intelligence-index leaderboard](https://artificialanalysis.ai/evaluations/artificial-analysis-intelligence-index) | | [AA-HLE](/benchmarks/aahle) | 60.4% | [Artificial Analysis: humanitys-last-exam leaderboard](https://artificialanalysis.ai/evaluations/humanitys-last-exam) | | [AA-Omniscience Index](/benchmarks/aaomniscienceindex) | 53.5% | [Artificial Analysis: omniscience leaderboard](https://artificialanalysis.ai/evaluations/omniscience) | | [AA-Omniscience Accuracy](/benchmarks/omniscienceaccuracy) | 58.3% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/gemini-4-carbon) | | [AA-Omniscience Hallucination Rate](/benchmarks/omnisciencehallucinationrate) | 11.4% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/gemini-4-carbon) | ## Instruction Following Benchmarks | Benchmark | Score | Source | |-----------|-------|--------| | [Gray Swan IPI (15 attempts)](/benchmarks/gray-swan-ipi) | 0.0% | [Google: Gemini 4 Carbon launch post](https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-carbon/) | ## Other Google Models - [Gemini 4 Argon](/models/gemini-4-argon) - Score: 82.3 - [Gemini 3.7 Flash](/models/gemini-3-7-flash) - Score: 66.55 - [Gemini 3.8 Flash](/models/gemini-3-8-flash) - Score: 66.27 - [Gemini 3.1 Pro](/models/gemini-3-1-pro) - Score: 64.45 - [Gemini 3.6 Flash](/models/gemini-3-6-flash) - Score: 62.46 - [Gemini 3.5 Flash](/models/gemini-3-5-flash) - Score: 61.45 - [Gemini 3 Pro](/models/gemini-3-pro) - Score: 60.73 - [Gemma 4 31B](/models/gemma-4-31b) - Score: 54.5 - [Gemini 3 Flash](/models/gemini-3-flash) - Score: 54.14 - [Gemini 2.5 Pro](/models/gemini-2-5-pro) - Score: 48.75 - [Gemini 3.5 Flash-Lite](/models/gemini-3-5-flash-lite) - Score: 46.75 - [Gemini 3.1 Flash-Lite](/models/gemini-3-1-flash-lite) - Score: 46.5 - [Gemma 4 26B A4B](/models/gemma-4-26b-a4b) - Score: 41.85 - [Gemini 2.5 Flash](/models/gemini-2-5-flash) - Score: 41.59 - [Gemma 4 12B](/models/gemma-4-12b) - Score: 35.5 - [Gemma 3 27B](/models/gemma-3-27b) - Score: 27.68 - [Gemini 1.5 Pro](/models/gemini-1-5-pro) - Score: 27.2 - [Gemma 4 E4B](/models/gemma-4-e4b) - Score: 26.6 - [Gemini 1.0 Pro](/models/gemini-1-0-pro) - Score: 11.03 - [Gemini 3 Pro Deep Think](/models/gemini-3-pro-deep-think) - Score: not computed - [Gemini 2.0 Flash](/models/gemini-2-0-flash) - Score: not computed - [Gemini 2.0 Flash-Lite](/models/gemini-2-0-flash-lite) - Score: not computed - [Gemini 2.5 Flash-Lite](/models/gemini-2-5-flash-lite) - Score: not computed - [Gemini 1.5 Flash](/models/gemini-1-5-flash) - Score: not computed - [Gemma 4 E2B](/models/gemma-4-e2b) - Score: not computed - [Gemma 2 27B](/models/gemma-2-27b) - Score: not computed - [EmbeddingGemma 2](/models/embeddinggemma-2) - Score: not computed - [Gemini 3.8 Flash TTS](/models/gemini-3-8-flash-tts) - Score: not computed - [Gemini 3.8 Flash-Lite TTS](/models/gemini-3-8-flash-lite-tts) - Score: not computed - [Gemini 3.8 Live](/models/gemini-3-8-live) - Score: not computed - [Gemini 3.8 Live Extended Thinking](/models/gemini-3-8-live-extended-thinking) - Score: not computed - [Gemini 3.8 Flash Cyber](/models/gemini-3-8-flash-cyber) - Score: not computed - [Gemini 3.5 Transcribe](/models/gemini-3-5-transcribe) - Score: not computed - [Gemini 3.5 Flash Cyber](/models/gemini-3-5-flash-cyber) - Score: not computed - [Gemini 3.1 Flash TTS Preview](/models/gemini-3-1-flash-tts-preview) - Score: not computed - [Gemini 3.1 Flash Live Preview](/models/gemini-3-1-flash-live-preview) - Score: not computed - [Gemini 2.5 Flash Native Audio Preview (12-2025)](/models/gemini-2-5-flash-native-audio-preview-12-2025) - Score: not computed - [Gemini 2.5 Flash TTS Preview](/models/gemini-2-5-flash-tts-preview) - Score: not computed - [Gemini 2.5 Pro TTS Preview](/models/gemini-2-5-pro-tts-preview) - Score: not computed