# Gemini 4 Hydrogen benchmark scores

Google · model · https://benchgap.net/model/gemini-4-hydrogen · data retrieved 2026-11-18

As of 2026-11-18, Gemini 4 Hydrogen (Google) has measured scores on 16 benchmarks and estimated scores on 70 more.

| Benchmark | Score | Source |
|---|---|---|
| [AA-GPQA Diamond](https://benchgap.net/b/aa-gpqa-diamond/current.md) | 90.9% | estimated ± 11.5 pp, low confidence |
| [AA-HLE](https://benchgap.net/b/aa-hle/current.md) | 53.7% | estimated ± 9.2 pp, medium confidence |
| [AA-SciCode](https://benchgap.net/b/aa-sci-code/current.md) | 62.1% | estimated ± 2.5 pp, high confidence |
| [Artificial Analysis Intelligence Index](https://benchgap.net/b/artificialanalysis/current.md) | 53.9% | measured |
| [CritPt](https://benchgap.net/b/critpt/current.md) | 28.7% | estimated ± 5.3 pp, medium confidence |
| [GDPval-AA](https://benchgap.net/b/gdpvalaanormalized/current.md) | 59.2% | estimated ± 1.7 pp, medium confidence |
| [GPQA Diamond](https://benchgap.net/b/gpqa-diamond/current.md) | 92.9% | estimated ± 2.5 pp, high confidence |
| [HLE](https://benchgap.net/b/hle/current.md) | 52.9% | estimated ± 10.3 pp, low confidence |
| [AA-Omniscience Accuracy](https://benchgap.net/b/omniscienceaccuracy/current.md) | 50.5% | measured |
| [Terminal-Bench 2.1](https://benchgap.net/b/terminal-bench%23terminal-bench-2-1/current.md) | 89.1% | estimated ± 5.4 pp, low confidence |
| [BrowseComp](https://benchgap.net/b/browsecomp/current.md) | 90.9% | estimated ± 11.3 pp, low confidence |
| [HLE w/ tools](https://benchgap.net/b/hlewithtools/current.md) | 66.4% | estimated ± 6.8 pp, low confidence |
| [AA Coding Index](https://benchgap.net/b/aa-coding-index/current.md) | 83.1% | estimated ± 1.2 pp, medium confidence |
| [AA-MMMU-Pro](https://benchgap.net/b/aa-mmmu-pro/current.md) | 86.6% | estimated ± 3.0 pp, medium confidence |
| [BioMysteryBench (human-difficult)](https://benchgap.net/b/biomysterybenchhumandifficult/current.md) | 46.8% | estimated ± 7.8 pp, low confidence |
| [AutomationBench](https://benchgap.net/b/automationbench/current.md) | 50.6% | estimated ± 6.1 pp, low confidence |
| [JobBench](https://benchgap.net/b/jobbench/current.md) | 72.5% | estimated ± 11.3 pp, low confidence |
| [SWE-bench Pro](https://benchgap.net/b/swe-bench-pro/current.md) | 84.2% | estimated ± 4.2 pp, high confidence |
| [MMLU-Pro](https://benchgap.net/b/mmlu-pro/current.md) | 85.5% | estimated ± 5.1 pp, low confidence |
| [GPQA](https://benchgap.net/b/gpqa/current.md) | 93.0% | estimated ± 6.9 pp, medium confidence |
| [MMLU](https://benchgap.net/b/mmlu/current.md) | 90.5% | estimated ± 0.9 pp, medium confidence |
| [Vals GPQA Diamond](https://benchgap.net/b/vals-gpqa-diamond/current.md) | 92.7% | estimated ± 5.7 pp, medium confidence |
| [Vals LiveCodeBench](https://benchgap.net/b/valslivecodebench/current.md) | 91.5% | estimated ± 3.0 pp, medium confidence |
| [Vals MMLU-Pro](https://benchgap.net/b/vals-mmlu-pro/current.md) | 88.4% | estimated ± 2.9 pp, high confidence |
| [AA MMLU-Pro](https://benchgap.net/b/aa-mmlu-pro/current.md) | 88.8% | estimated ± 0.8 pp, high confidence |
| [AA-AnalystAgent](https://benchgap.net/b/aa-analyst-agent/current.md) | 53.9% | estimated ± 2.7 pp, medium confidence |
| [ApprenticeBench](https://benchgap.net/b/apprenticebench/current.md) | 15.4% | estimated ± 12.5 pp, low confidence |
| [ARC-AGI-1](https://benchgap.net/b/arcagi1/current.md) | 91.4% | estimated ± 7.9 pp, low confidence |
| [ARC-AGI-2](https://benchgap.net/b/arc-agi-2/current.md) | 83.7% | estimated ± 14.6 pp, low confidence |
| [CursorBench 3.2](https://benchgap.net/b/cursor-bench32/current.md) | 74.6% | estimated ± 2.0 pp, medium confidence |
| [Terminal-Bench 3.0](https://benchgap.net/b/terminal-bench%23terminal-bench-3-0/current.md) | 44.2% | estimated ± 3.2 pp, medium confidence |
| [FrontierCode 1.1 Main](https://benchgap.net/b/frontiercode/current.md) | 51.1% | estimated ± 3.8 pp, low confidence |
| [FrontierSWE v2](https://benchgap.net/b/frontierswev2/current.md) | 53.1% | measured |
| [MazeBench](https://benchgap.net/b/mazebench/current.md) | 1.0% | measured |
| [ParseBench-1](https://benchgap.net/b/parse-bench-llama-index/current.md) | 73.0% | estimated ± 5.7 pp, low confidence |
| [Terminal-Bench 4.1](https://benchgap.net/b/terminal-bench41/current.md) | 56.4% | measured |
| [Terminal-Bench Hard](https://benchgap.net/b/terminal-bench-hard/current.md) | 68.1% | estimated ± 2.8 pp, low confidence |
| [Vals SWE-bench](https://benchgap.net/b/valsswebench/current.md) | 100.0% | estimated ± 3.7 pp, medium confidence |
| [Terminal-Bench 2.1 (Vals AI)](https://benchgap.net/b/vals-terminal-bench21/current.md) | 80.3% | estimated ± 6.9 pp, low confidence |
| [VulcanBench v3](https://benchgap.net/b/vulcanbench%23vulcanbench-v3/current.md) | 87.6% | estimated ± 3.9 pp, medium confidence |
| [CWE-Bench-AA](https://benchgap.net/b/aa-cwe-bench/current.md) | 62.9% | estimated ± 4.1 pp, medium confidence |
| [DeepsecBench-AA](https://benchgap.net/b/aa-deepsec-bench/current.md) | 31.8% | estimated ± 6.1 pp, low confidence |
| [Harvey LAB-AA v1.1](https://benchgap.net/b/aa-harvey-lab-v11/current.md) | 8.9% | estimated ± 3.5 pp, medium confidence |
| [HealthBench Professional (length-adjusted, Artificial Analysis)](https://benchgap.net/b/aa-health-bench-professional/current.md) | 62.3% | estimated ± 4.3 pp, medium confidence |
| [HealthBench Professional (raw, Artificial Analysis)](https://benchgap.net/b/aa-health-bench-professional-raw/current.md) | 69.9% | estimated ± 1.1 pp, medium confidence |
| [Bug Hunt Bench](https://benchgap.net/b/bug-hunt-bench/current.md) | 32.7% | measured |
| [Chartography (no tools)](https://benchgap.net/b/chartography/current.md) | 66.6% | measured |
| [Chartography (tools)](https://benchgap.net/b/chartographywithtools/current.md) | 90.2% | estimated ± 2.3 pp, medium confidence |
| [CursorBench 4.0](https://benchgap.net/b/cursor-bench40/current.md) | 54.3% | measured |
| [CWE-bench v1](https://benchgap.net/b/cwe-bench%23cwe-bench-v1/current.md) | 57.3% | estimated ± 5.3 pp, medium confidence |
| [DeepSWE](https://benchgap.net/b/deepswe/current.md) | 74.0% | estimated ± 4.1 pp, medium confidence |
| [DRACO](https://benchgap.net/b/draco/current.md) | 1.7% | estimated ± 0.7 pp, low confidence |
| [FrontierCode 2.0](https://benchgap.net/b/frontiercode-2/current.md) | 38.9% | measured |
| [HLE w/o tools](https://benchgap.net/b/hlenotools/current.md) | 59.0% | estimated ± 5.0 pp, high confidence |
| [OSWorld 2.1](https://benchgap.net/b/osworld-2-1/current.md) | 78.6% | estimated ± 6.1 pp, medium confidence |
| [OSWorld 2.1 Offline](https://benchgap.net/b/osworld-2-1-offline/current.md) | 77.6% | measured |
| [PostTrainBench v1.1](https://benchgap.net/b/posttrainbench%23posttrainbench-v1-1/current.md) | 48.6% | estimated ± 1.7 pp, medium confidence |
| [SWE-bench Multimodal](https://benchgap.net/b/swe-bench-multimodal/current.md) | 73.6% | estimated ± 8.3 pp, low confidence |
| [Terminal-Bench 4.0](https://benchgap.net/b/terminal-bench/current.md) | 58.3% | estimated ± 3.7 pp, high confidence |
| [Terminal-Bench-Science 0.1](https://benchgap.net/b/terminal-bench-science/current.md) | 51.4% | measured |
| [Toolathlon-Verified](https://benchgap.net/b/toolathlonverified/current.md) | 78.0% | estimated ± 1.8 pp, low confidence |
| [VulcanBench Frontier v4](https://benchgap.net/b/vulcanbench/current.md) | 92.2% | estimated ± 1.8 pp, high confidence |
| [AA AutomationBench](https://benchgap.net/b/aa-automation-bench/current.md) | 76.1% | measured |
| [GDP.pdf](https://benchgap.net/b/aa-gdp-pdf/current.md) | 27.6% | measured |
| [AA Terminal-Bench 4.0](https://benchgap.net/b/aa-terminal-bench4/current.md) | 53.5% | measured |
| [CWE-bench](https://benchgap.net/b/cwe-bench-v2/current.md) | 68.1% | measured |
| [MKA](https://benchgap.net/b/mka/current.md) | 53.4% | measured |
| [Hermes Bench](https://benchgap.net/b/hermesbench/current.md) | 100.0% | estimated ± 1.8 pp, low confidence |
| [Hermes Index](https://benchgap.net/b/hermesindex/current.md) | 88.9% | estimated ± 2.7 pp, low confidence |
| [ParseBench-2](https://benchgap.net/b/parsebench/current.md) | 82.6% | estimated ± 6.4 pp, low confidence |
| [ExploitGym](https://benchgap.net/b/exploitgym/current.md) | 13.9% | estimated ± 6.4 pp, medium confidence |
| [MMLU-Redux](https://benchgap.net/b/mmluredux/current.md) | 97.3% | estimated ± 0.8 pp, low confidence |
| [NL2Repo](https://benchgap.net/b/nl2repo/current.md) | 64.6% | estimated ± 6.5 pp, low confidence |
| [SuperGPQA](https://benchgap.net/b/supergpqa/current.md) | 99.9% | estimated ± 9.3 pp, low confidence |
| [PostTrainBench](https://benchgap.net/b/post-train-bench12/current.md) | 37.5% | estimated ± 2.4 pp, high confidence |
| [Finance Agent v2](https://benchgap.net/b/financeagentv2/current.md) | 56.2% | estimated ± 3.8 pp, medium confidence |
| [FrontierCode 1.1 Extended](https://benchgap.net/b/frontiercode11extended/current.md) | 62.1% | estimated ± 3.0 pp, medium confidence |
| [HealthBench (length-adjusted)](https://benchgap.net/b/healthbenchlengthadjusted/current.md) | 60.4% | estimated ± 3.7 pp, high confidence |
| [HealthBench Professional](https://benchgap.net/b/healthbenchprofessional/current.md) | 62.3% | estimated ± 4.2 pp, medium confidence |
| [HLE-Verified](https://benchgap.net/b/hleverified/current.md) | 46.9% | estimated ± 7.1 pp, low confidence |
| [ScarfBench](https://benchgap.net/b/scarfbench/current.md) | 69.3% | estimated ± 4.5 pp, low confidence |
| [STEMBench](https://benchgap.net/b/stembench/current.md) | 2.6% | estimated ± 0.2 pp, medium confidence |
| [Agents' Last Exam](https://benchgap.net/b/agentslastexam/current.md) | 50.1% | estimated ± 10.7 pp, low confidence |
| [OpenHarmony Bench v1.2](https://benchgap.net/b/openharmonybench/current.md) | 63.8% | estimated ± 11.0 pp, low confidence |
| [SWE-Marathon](https://benchgap.net/b/swemarathon/current.md) | 51.2% | estimated ± 2.1 pp, medium confidence |
| [BioBasicsBench](https://benchgap.net/b/biobasicsbench/current.md) | 34.1% | estimated ± 3.8 pp, medium confidence |
