# Gemini 4 Carbon benchmark scores

Google · model · https://benchgap.net/model/gemini-4-carbon · data retrieved 2026-10-29

As of 2026-10-29, Gemini 4 Carbon (Google) has measured scores on 16 benchmarks and estimated scores on 71 more.

| Benchmark | Score | Source |
|---|---|---|
| [AA-GPQA Diamond](https://benchgap.net/b/aa-gpqa-diamond/current.md) | 93.7% | estimated ± 6.6 pp, low confidence |
| [AA-HLE](https://benchgap.net/b/aa-hle/current.md) | 60.4% | measured |
| [AA-SciCode](https://benchgap.net/b/aa-sci-code/current.md) | 64.2% | measured |
| [CritPt](https://benchgap.net/b/critpt/current.md) | 36.0% | measured |
| [GDPval-AA](https://benchgap.net/b/gdpvalaanormalized/current.md) | 63.3% | estimated ± 2.9 pp, medium confidence |
| [GPQA Diamond](https://benchgap.net/b/gpqa-diamond/current.md) | 94.2% | estimated ± 2.3 pp, low confidence |
| [HLE](https://benchgap.net/b/hle/current.md) | 60.4% | estimated ± 9.7 pp, low confidence |
| [AA-LCR](https://benchgap.net/b/lcr/current.md) | 79.3% | measured |
| [LiveCodeBench v6](https://benchgap.net/b/livecodebench-v6/current.md) | 100.0% | estimated ± 4.9 pp, medium confidence |
| [SciCode](https://benchgap.net/b/scicode/current.md) | 63.6% | estimated ± 3.1 pp, medium confidence |
| [Terminal-Bench 2.1](https://benchgap.net/b/terminalbench21/current.md) | 87.4% | estimated ± 5.2 pp, low confidence |
| [BrowseComp](https://benchgap.net/b/browsecomp/current.md) | 96.6% | estimated ± 3.0 pp, low confidence |
| [HLE w/ tools](https://benchgap.net/b/hlewithtools/current.md) | 70.9% | estimated ± 5.2 pp, low confidence |
| [LongBench v2](https://benchgap.net/b/longbench-v2/current.md) | 62.0% | estimated ± 5.8 pp, low confidence |
| [AA Coding Index](https://benchgap.net/b/aa-coding-index/current.md) | 78.0% | estimated ± 3.0 pp, high confidence |
| [BioMysteryBench (human-difficult)](https://benchgap.net/b/biomysterybenchhumandifficult/current.md) | 50.3% | estimated ± 6.8 pp, low confidence |
| [SWE-bench Verified](https://benchgap.net/b/swe-bench-verified/current.md) | 100.0% | estimated ± 6.4 pp, low confidence |
| [AutomationBench](https://benchgap.net/b/automationbench/current.md) | 53.9% | measured |
| [CyberGym](https://benchgap.net/b/cybergym/current.md) | 87.9% | estimated ± 4.6 pp, medium confidence |
| [JobBench](https://benchgap.net/b/jobbench/current.md) | 69.1% | estimated ± 12.9 pp, low confidence |
| [SWE-bench Pro](https://benchgap.net/b/swe-bench-pro/current.md) | 84.6% | estimated ± 5.1 pp, medium confidence |
| [AA Agentic Index](https://benchgap.net/b/aa-agentic-index/current.md) | 58.2% | estimated ± 8.0 pp, low confidence |
| [MMLU-Pro](https://benchgap.net/b/mmlu-pro/current.md) | 86.2% | estimated ± 4.1 pp, medium confidence |
| [Artificial Analysis Intelligence Index](https://benchgap.net/b/artificialanalysis/current.md) | 59.4% | measured |
| [GPQA](https://benchgap.net/b/gpqa/current.md) | 93.7% | estimated ± 6.3 pp, low confidence |
| [AA-Omniscience Accuracy](https://benchgap.net/b/omniscienceaccuracy/current.md) | 58.3% | measured |
| [MMMLU](https://benchgap.net/b/mmmlu/current.md) | 93.2% | estimated ± 2.6 pp, low confidence |
| [AA MMLU-Pro](https://benchgap.net/b/aa-mmlu-pro/current.md) | 90.0% | estimated ± 0.7 pp, medium confidence |
| [AA-AnalystAgent](https://benchgap.net/b/aa-analyst-agent/current.md) | 54.8% | estimated ± 2.8 pp, medium confidence |
| [AA Tau3 Banking](https://benchgap.net/b/aa-tau3-banking/current.md) | 50.2% | estimated ± 3.8 pp, low confidence |
| [AA Terminal-Bench 2.1](https://benchgap.net/b/aa-terminal-bench21/current.md) | 87.5% | estimated ± 4.8 pp, low confidence |
| [ARC-AGI-1](https://benchgap.net/b/arcagi1/current.md) | 95.6% | estimated ± 7.6 pp, medium confidence |
| [ARC-AGI-2](https://benchgap.net/b/arc-agi-2/current.md) | 92.1% | estimated ± 14.6 pp, low confidence |
| [CursorBench 3.1](https://benchgap.net/b/cursor-bench31/current.md) | 79.0% | estimated ± 3.4 pp, low confidence |
| [CursorBench 3.2](https://benchgap.net/b/cursor-bench32/current.md) | 76.1% | estimated ± 4.1 pp, low confidence |
| [FrontierCode 1.1 Main](https://benchgap.net/b/frontiercode/current.md) | 51.8% | estimated ± 3.8 pp, low confidence |
| [FrontierSWE v2](https://benchgap.net/b/frontierswev2/current.md) | 61.2% | measured |
| [MazeBench](https://benchgap.net/b/mazebench/current.md) | 25.5% | estimated ± 3.0 pp, medium confidence |
| [Vals GPQA Diamond](https://benchgap.net/b/vals-gpqa-diamond/current.md) | 93.3% | estimated ± 5.3 pp, low confidence |
| [Vals MMLU-Pro](https://benchgap.net/b/vals-mmlu-pro/current.md) | 88.6% | estimated ± 2.1 pp, medium confidence |
| [Vals SWE-bench](https://benchgap.net/b/valsswebench/current.md) | 99.5% | estimated ± 4.9 pp, medium confidence |
| [Terminal-Bench 2.1 (Vals AI)](https://benchgap.net/b/vals-terminal-bench21/current.md) | 80.9% | estimated ± 9.4 pp, low confidence |
| [AA AutomationBench](https://benchgap.net/b/aa-automation-bench/current.md) | 77.8% | measured |
| [CWE-Bench-AA](https://benchgap.net/b/aa-cwe-bench/current.md) | 61.9% | estimated ± 6.0 pp, low confidence |
| [AA Cyber Index](https://benchgap.net/b/aa-cyber-index/current.md) | 46.3% | estimated ± 9.4 pp, medium confidence |
| [DeepsecBench-AA](https://benchgap.net/b/aa-deepsec-bench/current.md) | 39.4% | estimated ± 5.3 pp, low confidence |
| [GDP.pdf](https://benchgap.net/b/aa-gdp-pdf/current.md) | 28.4% | measured |
| [AA ITBench](https://benchgap.net/b/aa-itbench/current.md) | 54.3% | estimated ± 4.3 pp, medium confidence |
| [AA Terminal-Bench 4.0](https://benchgap.net/b/aa-terminal-bench4/current.md) | 65.2% | measured |
| [Bug Hunt Bench](https://benchgap.net/b/bug-hunt-bench/current.md) | 42.2% | estimated ± 7.6 pp, medium confidence |
| [CursorBench 4.0](https://benchgap.net/b/cursor-bench40/current.md) | 55.7% | estimated ± 2.7 pp, high confidence |
| [CWE-bench v1](https://benchgap.net/b/cwe-bench-v1/current.md) | 71.0% | measured |
| [DeepSWE](https://benchgap.net/b/deepswe/current.md) | 73.3% | estimated ± 4.5 pp, medium confidence |
| [FrontierCode 2.0](https://benchgap.net/b/frontiercode-2/current.md) | 38.6% | estimated ± 4.9 pp, high confidence |
| [GraphWalks BFS 256K–1M](https://benchgap.net/b/graphwalks-bfs-256k-1m/current.md) | 96.2% | measured |
| [HLE w/o tools](https://benchgap.net/b/hlenotools/current.md) | 63.8% | estimated ± 4.6 pp, medium confidence |
| [OSWorld 2.0](https://benchgap.net/b/osworld2/current.md) | 53.0% | estimated ± 9.2 pp, low confidence |
| [OSWorld 2.1](https://benchgap.net/b/osworld-2-1/current.md) | 79.9% | estimated ± 2.8 pp, low confidence |
| [PostTrainBench v1.1](https://benchgap.net/b/posttrainbench-v1-1/current.md) | 44.2% | estimated ± 4.3 pp, medium confidence |
| [Terminal-Bench 4.0](https://benchgap.net/b/terminal-bench-4/current.md) | 64.6% | estimated ± 5.7 pp, medium confidence |
| [Toolathlon-Verified](https://benchgap.net/b/toolathlonverified/current.md) | 78.5% | estimated ± 1.3 pp, low confidence |
| [OSWorld 2.1 Offline](https://benchgap.net/b/osworld-2-1-offline/current.md) | 81.5% | measured |
| [ARC-AGI-3](https://benchgap.net/b/arcagi3/current.md) | 48.0% | estimated ± 7.7 pp, low confidence |
| [ARC-AGI-3 Provider Adapter](https://benchgap.net/b/arc-agi-3-provider-adapter/current.md) | 98.6% | estimated ± 7.5 pp, low confidence |
| [Hermes Bench](https://benchgap.net/b/hermesbench/current.md) | 73.8% | estimated ± 0.3 pp, low confidence |
| [Hermes Index](https://benchgap.net/b/hermesindex/current.md) | 61.0% | estimated ± 2.6 pp, low confidence |
| [ExploitBench](https://benchgap.net/b/exploitbench/current.md) | 100.0% | estimated ± 10.7 pp, low confidence |
| [ExploitGym](https://benchgap.net/b/exploitgym/current.md) | 53.5% | measured |
| [MMLU-Redux](https://benchgap.net/b/mmluredux/current.md) | 98.2% | estimated ± 0.8 pp, low confidence |
| [NL2Repo](https://benchgap.net/b/nl2repo/current.md) | 74.7% | estimated ± 7.4 pp, low confidence |
| [SuperGPQA](https://benchgap.net/b/supergpqa/current.md) | 100.0% | estimated ± 9.3 pp, low confidence |
| [HealthBench Hard](https://benchgap.net/b/healthbench-hard/current.md) | 34.4% | estimated ± 8.6 pp, low confidence |
| [React Native Evals](https://benchgap.net/b/reactnativeevals/current.md) | 82.7% | estimated ± 4.7 pp, low confidence |
| [Finance Agent v2](https://benchgap.net/b/financeagentv2/current.md) | 63.5% | estimated ± 4.5 pp, low confidence |
| [BioMysteryBench (human-solvable)](https://benchgap.net/b/biomysterybenchhumansolvable/current.md) | 89.6% | estimated ± 0.6 pp, low confidence |
| [HealthBench (raw)](https://benchgap.net/b/healthbench/current.md) | 65.4% | estimated ± 6.0 pp, medium confidence |
| [HealthBench (length-adjusted)](https://benchgap.net/b/healthbenchlengthadjusted/current.md) | 60.7% | estimated ± 3.3 pp, medium confidence |
| [HealthBench Professional](https://benchgap.net/b/healthbenchprofessional/current.md) | 65.4% | estimated ± 4.5 pp, medium confidence |
| [HealthBench Professional (raw)](https://benchgap.net/b/healthbenchprofessionalraw/current.md) | 75.2% | estimated ± 4.5 pp, high confidence |
| [HLE-Verified](https://benchgap.net/b/hleverified/current.md) | 54.4% | estimated ± 6.8 pp, low confidence |
| [LABBench2](https://benchgap.net/b/labbench2/current.md) | 88.5% | estimated ± 2.4 pp, low confidence |
| [STEMBench](https://benchgap.net/b/stembench/current.md) | 2.7% | estimated ± 0.2 pp, medium confidence |
| [Agents' Last Exam](https://benchgap.net/b/agentslastexam/current.md) | 51.7% | estimated ± 9.6 pp, low confidence |
| [OpenHarmony Bench](https://benchgap.net/b/openharmonybench/current.md) | 58.9% | estimated ± 2.4 pp, medium confidence |
| [SEC-Bench Pro](https://benchgap.net/b/secbenchpro/current.md) | 88.2% | measured |
| [MRCRv2](https://benchgap.net/b/mrcrv2/current.md) | 85.7% | estimated ± 11.3 pp, low confidence |
| [MMLongBench-Doc](https://benchgap.net/b/mmlongbenchdoc/current.md) | 61.4% | estimated ± 2.6 pp, low confidence |