Google: Gemini 4 Argon
Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to k…
google/gemini-4-argon-20261013
Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across long, multi-step tasks and to turn long documents mixing text, tables, charts and images into a single grounded output. It leads the Vals Index across finance, legal, coding and tax work, and supports long decode of up to 1M output tokens in a single response.
Specifications & capabilities
- Input
- audio, file, image, text, video
- Output
- text
- Context window · tokens
- 1048576
- Capabilities
- audioInput, fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, videoInput, visionInput, webSearch
Description source ↗Evaluations
1–20 / 96
1,576.34
- source id
- lmarena
- leaderboard name
- LMArena Text German
- dimension
- general
- metric
- Arena rating
- rank
- 1
- sample size
- 283
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Argon (High)
- confidence lower
- 1537.8659685574082
- confidence upper
- 1614.814463225064
Original result ↗1,567.795
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control German
- dimension
- style
- metric
- Arena rating
- rank
- 1
- sample size
- 283
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Argon (High)
- confidence lower
- 1529.4276481126258
- confidence upper
- 1606.161437092244
Original result ↗1,562.643
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Chinese
- dimension
- factuality
- metric
- Arena rating
- rank
- 1
- sample size
- 1357
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Argon (High)
- confidence lower
- 1546.791524561695
- confidence upper
- 1578.4939830671137
Original result ↗1,550.617
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Mathematical
- dimension
- general
- metric
- Arena rating
- rank
- 1
- sample size
- 1175
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Argon (High)
- confidence lower
- 1532.618560202226
- confidence upper
- 1568.6151093478697
Original result ↗1,550.198
- source id
- lmarena
- leaderboard name
- LMArena Text French
- dimension
- general
- metric
- Arena rating
- rank
- 1
- sample size
- 749
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Argon (High)
- confidence lower
- 1526.5672315545064
- confidence upper
- 1573.8288344909952
Original result ↗1,547.907
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control French
- dimension
- style
- metric
- Arena rating
- rank
- 1
- sample size
- 749
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Argon (High)
- confidence lower
- 1524.0593680425545
- confidence upper
- 1571.7551149011097
Original result ↗1,545.623
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Life And Physical And Social Science
- dimension
- general
- metric
- Arena rating
- rank
- 1
- sample size
- 3189
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Argon (High)
- confidence lower
- 1534.2044690488424
- confidence upper
- 1557.0412762633619
Original result ↗1,543.877
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Longer Query
- dimension
- style
- metric
- Arena rating
- rank
- 1
- sample size
- 8754
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Argon (High)
- confidence lower
- 1536.1861071140752
- confidence upper
- 1551.5676228405262
Original result ↗1,540.05
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Legal And Government
- dimension
- general
- metric
- Arena rating
- rank
- 1
- sample size
- 1571
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Argon (High)
- confidence lower
- 1523.8610752542402
- confidence upper
- 1556.2388342319732
Original result ↗1,539.668
- source id
- lmarena
- leaderboard name
- LMArena Text Polish
- dimension
- general
- metric
- Arena rating
- rank
- 1
- sample size
- 309
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Argon (High)
- confidence lower
- 1504.3544539248146
- confidence upper
- 1574.9824111165276
Original result ↗1,539.121
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Mathematical
- dimension
- style
- metric
- Arena rating
- rank
- 1
- sample size
- 1175
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Argon (High)
- confidence lower
- 1521.1412527470877
- confidence upper
- 1557.1011612324796
Original result ↗1,538.336
- source id
- lmarena
- leaderboard name
- LMArena Text Math
- dimension
- general
- metric
- Arena rating
- rank
- 1
- sample size
- 1046
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Argon (High)
- confidence lower
- 1519.5918336150314
- confidence upper
- 1557.0795571890726
Original result ↗1,536.227
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Life And Physical And Social Science
- dimension
- style
- metric
- Arena rating
- rank
- 1
- sample size
- 3189
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Argon (High)
- confidence lower
- 1524.7134607524267
- confidence upper
- 1547.7397378599576
Original result ↗1,535.739
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Industry Medicine And Healthcare
- dimension
- factuality
- metric
- Arena rating
- rank
- 1
- sample size
- 1143
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Argon (High)
- confidence lower
- 1518.045427459269
- confidence upper
- 1553.432681545938
Original result ↗1,534.674
- source id
- lmarena
- leaderboard name
- LMArena Text Creative Writing
- dimension
- general
- metric
- Arena rating
- rank
- 1
- sample size
- 4738
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Argon (High)
- confidence lower
- 1524.479525809187
- confidence upper
- 1544.8689028823774
Original result ↗1,532.397
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Industry Life And Physical And Social Science
- dimension
- factuality
- metric
- Arena rating
- rank
- 1
- sample size
- 2974
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Argon (High)
- confidence lower
- 1521.7308607308457
- confidence upper
- 1543.0621991601124
Original result ↗1,531.329
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Multi Turn
- dimension
- factuality
- metric
- Arena rating
- rank
- 1
- sample size
- 2533
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Argon (High)
- confidence lower
- 1519.3119633745666
- confidence upper
- 1543.346804197901
Original result ↗1,530.803
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Math
- dimension
- style
- metric
- Arena rating
- rank
- 1
- sample size
- 1046
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Argon (High)
- confidence lower
- 1512.0976643118242
- confidence upper
- 1549.5088472044063
Original result ↗1,528.786
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Instruction Following
- dimension
- style
- metric
- Arena rating
- rank
- 1
- sample size
- 7180
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Argon (High)
- confidence lower
- 1520.6250004538292
- confidence upper
- 1536.9476200851664
Original result ↗1,526.634
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Medicine And Healthcare
- dimension
- style
- metric
- Arena rating
- rank
- 1
- sample size
- 1322
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Gemini 4 Argon (High)
- confidence lower
- 1509.2538950572316
- confidence upper
- 1544.013820792242
Original result ↗Published prices
61–61 / 61
$0.01
- Inference provider
- vercelAIGatewayCatalog
- Platform
- vertex
- Unit
- request
- Currency
- USD
- Billing conditions
- charge
- web_search
- endpoint
- vertex | google/gemini-4-argon
- model_type
- language
- billing_scope
- via Vercel AI Gateway
- Billing label
- Web search
- Pricing via
- Vercel AI Gateway
Provider specifications & access
1–4 / 4
- source model id
- gemini-4-argon
- hosting
- gateway
- context length
- 1048576
- max output tokens
- 1000000
- capabilities
- reasoning
- structuredOutputs
- toolCalling
- videoInput
- visionInput
- webSearch
- source model id
- Gemini 4 Argon
- hosting
- copilot-subscription
- license
- CC-BY-4.0
- attribution
- GitHub and github/docs contributors
- plans
- max
- true
- pro
- false
- business
- true
- pro_plus
- true
- enterprise
- true
- clients
- vs
- true
- cli
- true
- xcode
- true
- dotcom
- false
- vscode
- true
- eclipse
- true
- jetbrains
- true
- access scope
- Published plan/client flags; account settings, organization policy and additional access conditions apply
- availability
- supported
- release status
- GA
- billing scope
- Copilot subscription usage; not an unconditional inference API rate
- billing rates
- tier
- Default
- unit
- tokens_per_million
- input
- 2
- output
- 10
- currency
- USD
- original
- tier
- Default
- input
- $2.00
- model
- Gemini 4 Argon[^gemini-4-argon-promo]
- output
- $10.00
- category
- Powerful
- provider
- google
- threshold
- Not applicable
- cached_input
- $0.10
- release_status
- GA
- threshold
- Not applicable
- cached_input
- 0.1
- footnote_restrictions
- true
- requires_subscription
- true
- comparison
- name
- Gemini 4 Argon
- excels_at
- Thorough work that tests edge cases before finishing
- task_area
- Complex coding, agentic, and reasoning tasks
- further_reading
- [Gemini 4 Argon](https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-4-Argon-Model-Card.pdf)
- source model id
- google/gemini-4-argon
- hosting
- third-party
- context length
- 1048576
- max output tokens
- 65536
- source model id
- google/gemini-4-argon
- hosting
- vercel-gateway
- context length
- 1000000
- max output tokens
- 1000000
- capabilities
- promptCaching
- reasoning
- structuredOutputs
- toolCalling
- videoInput
- visionInput
- webSearch
Safety assessments
1–1 / 1
41 / 100
- source id
- stanfordFMTI
- canonical model id
- google/gemini-4-argon-20261013
- taxonomy
- transparency
- hazard category
- transparency
- hazard name
- Organization transparency
- policy area
- Google
- assessment type
- organization-level disclosure
- metric
- disclosure_score
- result label
- 41 / 100
- sample size
- 100
- updated at
- 2026-11-09T18:08:05.227Z
Source specification observations
1–8 / 8
- field
- context_length
- value
- 1048576
- normalized value
- 1048576
- scope
- source-model
- source id
- cloudflareWorkersAI
- confidence
- 1
- field
- context_length
- value
- 1048576
- normalized value
- 1048576
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 1048576
- normalized value
- 1048576
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- context_length
- value
- 1000000
- normalized value
- 1000000
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
- field
- max_output_tokens
- value
- 65536
- normalized value
- 65536
- scope
- source-model
- source id
- cloudflareWorkersAI
- confidence
- 1
- field
- max_output_tokens
- value
- 943718
- normalized value
- 943718
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 943718
- normalized value
- 943718
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 1000000
- normalized value
- 1000000
- scope
- source-model
- source id
- vercelAIGatewayCatalog
- confidence
- 1
Explore more models