Google model product
Gemini 4 Hydrogen is Google's model for everyday coding and agentic workflows, with four thinking levels and a 1M-token context window.
Updated Nov 22, 2026. Default version: Gemini 4 Hydrogen
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for Gemini 4 Hydrogen.
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkVending-Bench 2 | Score14,549.00 usd | Rank03 | Participants7 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Steerability | Score17.44% | Rank03 | Participants50 | Percentile95.92% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Task Outcome Explicit | Score15.71% | Rank03 | Participants50 | Percentile95.92% | EvidenceA | Evaluated |
| BenchmarkAgents' Last Exam | Score71.60% | Rank04 | Participants33 | Percentile90.63% | EvidenceC | Evaluated |
| BenchmarkLM Arena Agent Praise Complaint | Score29.26% | Rank04 | Participants50 | Percentile93.88% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,493.59 rating | Rank05 | Participants135 | Percentile97.01% | EvidenceA | Evaluated |
| BenchmarkChartography (no tools) | Score66.60% | Rank05 | Participants7 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkRamp SWE-Bench v2 | Score71.60% | Rank05 | Participants16 | Percentile73.33% | EvidenceB | Evaluated |
| BenchmarkLM Arena Agent Leaderboard | Score13.52% | Rank06 | Participants50 | Percentile89.80% | EvidenceA | Evaluated |
| BenchmarkOSWorld 2.1 (partial) | Score77.60% | Rank06 | Participants11 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkRamp SWE-Bench v2 (Bash) | Score70.80% | Rank06 | Participants22 | Percentile76.19% | EvidenceB | Evaluated |
| BenchmarkLM Arena Text | Score1,501.78 rating | Rank07 | Participants222 | Percentile97.29% | EvidenceA | Evaluated |
| BenchmarkLM Arena Webdev | Score1,700.63 rating | Rank08 | Participants112 | Percentile93.69% | EvidenceA | Evaluated |
| BenchmarkTerminal-Bench-Science 0.1 | Score51.40% | Rank14 | Participants17 | Percentile18.75% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,489.78 rating | Rank14 | Participants222 | Percentile94.12% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Tool Hallucination | Score0.71% | Rank23 | Participants50 | Percentile55.10% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Bash Reliability | Score-4.55% | Rank31 | Participants50 | Percentile38.78% | EvidenceA | Evaluated |
Preference and agent-evaluation results for the default version.
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext | Categorychinese | Rank01 | Rating / score1,628.95 | Votes342 | ObservationsN/A | Result date |
| Arenatext style control | Categorychinese | Rank01 | Rating / score1,598.77 | Votes342 | ObservationsN/A | Result date |
| Arenaagent steerability | Categoryoverall | Rank03 | Rating / score0.17 | VotesN/A | Observations38K | Result date |
| Arenaagent task outcome explicit | Categoryoverall | Rank03 | Rating / score0.16 | VotesN/A | Observations4.7K | Result date |
| Arenatext | Categoryindustry legal and government | Rank03 | Rating / score1,527.28 | Votes380 | ObservationsN/A | Result date |
| Arenaagent praise complaint | Categoryoverall | Rank04 | Rating / score0.29 | VotesN/A | Observations1.8K | Result date |
| Arenatext | Categoryindustry entertainment and sports and media | Rank04 | Rating / score1,499.46 | Votes1,199 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryinstruction following | Rank04 | Rating / score1,512.12 | Votes1,693 | ObservationsN/A | Result date |
| Arenatext factuality | Categorylonger query | Rank04 | Rating / score1,522.55 | Votes2,067 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry mathematical | Rank05 | Rating / score1,537.17 | Votes257 | ObservationsN/A | Result date |
| Arenatext factuality | Categorynon english | Rank05 | Rating / score1,486.54 | Votes3,112 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryoverall | Rank05 | Rating / score1,493.59 | Votes4,743 | ObservationsN/A | Result date |
| Arenaagent | Categoryoverall | Rank06 | Rating / score0.14 | VotesN/A | Observations2M | Result date |
| Arenatext | Categorycreative writing | Rank06 | Rating / score1,508.34 | Votes1,030 | ObservationsN/A | Result date |
| Arenatext | Categoryexpert | Rank06 | Rating / score1,552.61 | Votes420 | ObservationsN/A | Result date |
| Arenatext | Categorylonger query | Rank06 | Rating / score1,520.81 | Votes2,067 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryexclude ties | Rank06 | Rating / score1,506.70 | Votes3,553 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts | Rank06 | Rating / score1,520.86 | Votes3,009 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank06 | Rating / score1,482.69 | Votes1,199 | ObservationsN/A | Result date |
| Arenatext | Categoryexclude ties | Rank07 | Rating / score1,517.07 | Votes3,553 | ObservationsN/A | Result date |
| Arenatext | Categorynon english | Rank07 | Rating / score1,494.94 | Votes3,112 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank07 | Rating / score1,501.78 | Votes4,743 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycreative writing | Rank07 | Rating / score1,485.32 | Votes1,030 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry entertainment and sports and media | Rank07 | Rating / score1,481.92 | Votes1,199 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry life and physical and social science | Rank07 | Rating / score1,514.46 | Votes687 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry mathematical | Rank07 | Rating / score1,522.68 | Votes257 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev-html | Rank07 | Rating / score1,718.47 | Votes274 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts | Rank08 | Rating / score1,517.24 | Votes3,009 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry writing and literature and language | Rank08 | Rating / score1,498.95 | Votes1,426 | ObservationsN/A | Result date |
| Arenatext | Categoryinstruction following | Rank08 | Rating / score1,515.03 | Votes1,693 | ObservationsN/A | Result date |
Official vendor API pricing appears first, followed by individual provider offers.
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderMerge Gateway | Provider model IDgoogle/gemini-4-hydrogen | Regionglobal | Input / 1M$1.5 | Output / 1M$7.5 | Context1M | Updated |
| ProviderVertex | Provider model IDgemini-4-hydrogen | Regionglobal | Input / 1M$1.5 | Output / 1M$7.5 | Context1M | Updated |
| ProviderVercel AI Gateway | Provider model IDgoogle/gemini-4-hydrogen | Regionglobal | Input / 1M$1.5 | Output / 1M$7.5 | Context1M | Updated |
| ProviderNanoGPT | Provider model IDgoogle/gemini-4-hydrogen | Regionglobal | Input / 1M$1.5 | Output / 1M$7.5 | Context1M | Updated |
| ProviderOpenCode | Provider model IDgemini-4-hydrogen | Regionglobal | Input / 1M$1.5 | Output / 1M$7.5 | Context1M | Updated |
| ProviderKilo Gateway | Provider model IDgoogle/gemini-4-hydrogen | Regionglobal | Input / 1M$1.5 | Output / 1M$7.5 | Context1M | Updated |
| ProviderGoogle | Provider model IDgemini-4-hydrogen | Regionglobal | Input / 1M$1.5 | Output / 1M$7.5 | Context1M | Updated |
| ProviderEden AI | Provider model IDgoogle/gemini-4-hydrogen | Regionglobal | Input / 1M$1.5 | Output / 1M$7.5 | Context1M | Updated |
| ProviderOpenRouter | Provider model IDgoogle/gemini-4-hydrogen | Regionglobal | Input / 1M$1.5 | Output / 1M$7.5 | Context1M | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDgemini-4-hydrogen | Regionglobal | Input / 1M$1.5 | Output / 1M$7.5 | Context1M | Updated |
| ProviderGitHub Copilot | Provider model IDgemini-4-hydrogen | Regionglobal | Input / 1M$1.5 | Output / 1M$7.5 | Context1M | Updated |
| ProviderOfox | Provider model IDgoogle/gemini-4-hydrogen | Regionglobal | Input / 1M$1.5 | Output / 1M$7.5 | Context1M | Updated |
| ProviderCrossModel | Provider model IDgemini/gemini-4-hydrogen | Regionglobal | Input / 1M$1.5 | Output / 1M$7.5 | Context1M | Updated |
| ProviderCloudflare AI Gateway | Provider model IDgoogle/gemini-4-hydrogen | Regionglobal | Input / 1M$1.5 | Output / 1M$7.5 | Context1M | Updated |
| ProviderRequesty | Provider model IDgemini-4-hydrogen | Regionglobal | Input / 1M$1.5 | Output / 1M$7.5 | Context1M | Updated |
| ProviderVivgrid | Provider model IDgemini-4-hydrogen | Regionglobal | Input / 1M$1.5 | Output / 1M$7.5 | Context1M | Updated |
| ProviderCortecs | Provider model IDgemini-4-hydrogen | Regionglobal | Input / 1M$1.69 | Output / 1M$8.44 | Context1M | Updated |
| ProviderVenice AI | Provider model IDgemini-4-hydrogen | Regionglobal | Input / 1M$1.88 | Output / 1M$9.38 | Context1M | Updated |
Provider-specific output speed and catalog latency for Gemini 4 Hydrogen. Runtime does not affect the capability score.
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Technical details for the model's default version.
Available versions of this model. The score column identifies the version used in the overall ranking.
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionGemini 4 Hydrogen | Released | LLMBoard85.10 | ParametersN/A | Context1M | Max output1M | Open weightsNo | LicenseProprietary |
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Key information about Gemini 4 Hydrogen and its available data.
Gemini 4 Hydrogen is a Google LLM for everyday coding and agentic workflows. It has four thinking levels and a 1M-token context window.
Data as of 2026-11-21.
Common questions about Gemini 4 Hydrogen.
Gemini 4 Hydrogen's default version was released on Nov 12, 2026.
Gemini 4 Hydrogen's official API price is $1.5 per million input tokens and $7.5 per million output tokens via Google. The lowest tracked third-party offer starts at $1.5 input and $7.5 output via Merge Gateway.
Gemini 4 Hydrogen was created by Google.
The default version has a 1M token context window.
No. The default version is not marked as having publicly available weights.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
18 provider offerings are linked to the default version.