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

61–80 / 96

LMArena

1,513.58

source id
lmarena
leaderboard name
LMArena Text Style Control Non English
dimension
style
metric
Arena rating
rank
2
sample size
12333
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1507.021788121308
confidence upper
1520.1377340163708
Original result ↗

LMArena

1,510.352

source id
lmarena
leaderboard name
LMArena Text Factuality Industry Mathematical
dimension
factuality
metric
Arena rating
rank
2
sample size
919
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1491.2074076265299
confidence upper
1529.4966098217528
Original result ↗

LMArena

1,506.203

source id
lmarena
leaderboard name
LMArena Text Factuality Creative Writing
dimension
factuality
metric
Arena rating
rank
2
sample size
4693
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1497.8206585572366
confidence upper
1514.584934244043
Original result ↗

LMArena

1,500.177

source id
lmarena
leaderboard name
LMArena Text Factuality Industry Entertainment And Sports And Media
dimension
factuality
metric
Arena rating
rank
2
sample size
5355
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1492.0053932182593
confidence upper
1508.3493267583597
Original result ↗

OpenRouter Benchmarks

78.667%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Google
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
2
sample size
50
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
1
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
tau_bench_verified_airline
name
tau2-bench Verified Airline
record_kind
aggregate
provider_name
Google
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-14T15:16:05.578Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
tau2-bench Verified Airline · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
50
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.786667
cost_per_task_usd
0.49828548
output_tokens_per_task
21971.04
latency_seconds_per_task
348.41768
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
36
benchmark_evaluation
true
openrouter_permaslug
google/gemini-4-argon-20261013
source model id
google/gemini-4-argon-20261013
Original result ↗

LMArena

1,547.754

source id
lmarena
leaderboard name
LMArena Text Style Control Expert
dimension
style
metric
Arena rating
rank
3
sample size
1971
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1533.3944525501106
confidence upper
1562.113841307251
Original result ↗

LMArena

1,540.032

source id
lmarena
leaderboard name
LMArena Text Coding
dimension
general
metric
Arena rating
rank
3
sample size
4614
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1530.511457928374
confidence upper
1549.5529057402375
Original result ↗

LMArena

1,538.389

source id
lmarena
leaderboard name
LMArena Text Factuality Hard Prompts English
dimension
factuality
metric
Arena rating
rank
3
sample size
4738
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1530.0450881850654
confidence upper
1546.7336420194254
Original result ↗

LMArena

1,536.464

source id
lmarena
leaderboard name
LMArena Text Factuality Industry Software And It Services
dimension
factuality
metric
Arena rating
rank
3
sample size
6872
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1529.2198117518221
confidence upper
1543.7081995096855
Original result ↗

LMArena

1,529.331

source id
lmarena
leaderboard name
LMArena Text Style Control Japanese
dimension
style
metric
Arena rating
rank
3
sample size
301
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1491.8673807528153
confidence upper
1566.7941019478642
Original result ↗

LMArena

1,524.716

source id
lmarena
leaderboard name
LMArena Text Factuality Hard Prompts
dimension
factuality
metric
Arena rating
rank
3
sample size
12589
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1518.9075397824213
confidence upper
1530.5236507794134
Original result ↗

LMArena

1,516.026

source id
lmarena
leaderboard name
LMArena Text Factuality Instruction Following
dimension
factuality
metric
Arena rating
rank
3
sample size
7166
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1508.965205033085
confidence upper
1523.0871589900562
Original result ↗

LMArena

1,515.983

source id
lmarena
leaderboard name
LMArena Text Factuality Exclude Ties
dimension
factuality
metric
Arena rating
rank
3
sample size
15043
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1510.0367732210836
confidence upper
1521.9286618105273
Original result ↗

LMArena

1,515.327

source id
lmarena
leaderboard name
LMArena Text Spanish
dimension
general
metric
Arena rating
rank
3
sample size
767
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1493.0335497823967
confidence upper
1537.6197844585445
Original result ↗

LMArena

1,511.276

source id
lmarena
leaderboard name
LMArena Text Factuality Industry Writing And Literature And Language
dimension
factuality
metric
Arena rating
rank
3
sample size
5973
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1503.8242580630779
confidence upper
1518.7280132019846
Original result ↗

LMArena

1,509.705

source id
lmarena
leaderboard name
LMArena Text Factuality English
dimension
factuality
metric
Arena rating
rank
3
sample size
7444
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1502.8358431687047
confidence upper
1516.57458466648
Original result ↗

LMArena

1,548.935

source id
lmarena
leaderboard name
LMArena Text Factuality Coding
dimension
factuality
metric
Arena rating
rank
4
sample size
4581
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1540.2870883206215
confidence upper
1557.5837813915007
Original result ↗

LMArena

1,537.708

source id
lmarena
leaderboard name
LMArena Text Factuality Expert
dimension
factuality
metric
Arena rating
rank
4
sample size
1719
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1523.6165998969923
confidence upper
1551.798632747939
Original result ↗

LMArena

1,497.844

source id
lmarena
leaderboard name
LMArena Text Factuality Overall
dimension
factuality
metric
Arena rating
rank
4
sample size
19787
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1493.0900016132125
confidence upper
1502.597804505619
Original result ↗

LMArena

1,489.028

source id
lmarena
leaderboard name
LMArena Text Factuality Non English
dimension
factuality
metric
Arena rating
rank
4
sample size
12333
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 4 Argon (High)
confidence lower
1483.1251915833393
confidence upper
1494.9308202857053
Original result ↗

Published prices

1–20 / 61

gemini-4-argon ↗

$0.05

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Cached input tokens (per 1M)

gemini-4-argon ↗

$0.90

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
input_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Input tokens (per 1M)

gemini-4-argon ↗

$4.50

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
output_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Output tokens (per 1M)

google/gemini-4-argon ↗

$0.10

Inference provider
cloudflareWorkersAI
Platform
Google Vertex AI
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
Billing label
Cached input tokens (per 1M)
Pricing via
Cloudflare AI Gateway

google/gemini-4-argon ↗

$2.00

Inference provider
cloudflareWorkersAI
Platform
Google Vertex AI
Unit
input_tokens_per_million
Currency
USD
Billing conditions
Billing label
Input tokens (per 1M)
Pricing via
Cloudflare AI Gateway

google/gemini-4-argon ↗

$10.00

Inference provider
cloudflareWorkersAI
Platform
Google Vertex AI
Unit
output_tokens_per_million
Currency
USD
Billing conditions
Billing label
Output tokens (per 1M)
Pricing via
Cloudflare AI Gateway

google/gemini-4-argon ↗

$0.10

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions

google/gemini-4-argon ↗

$0.19

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_write_tokens_per_million
Currency
USD
Billing conditions

google/gemini-4-argon ↗

$2.00

Inference provider
openRouter
Platform
OpenRouter
Unit
input_tokens_per_million
Currency
USD
Billing conditions

google/gemini-4-argon ↗

$10.00

Inference provider
openRouter
Platform
OpenRouter
Unit
output_tokens_per_million
Currency
USD
Billing conditions

google/gemini-4-argon ↗

$0.10

Inference provider
vercelAIGatewayCatalog
Platform
google
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
google | google/gemini-4-argon
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

google/gemini-4-argon ↗

$0.05

Inference provider
vercelAIGatewayCatalog
Platform
google
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
google | google/gemini-4-argon
model_type
language
service_tier
flex
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

Provider specifications & access

1–4 / 4

gemini-4-argon ↗

source model id
gemini-4-argon
hosting
gateway
platforms
  • Cheaper Inference
context length
1048576
max output tokens
1000000
architecture
input_modalities
  • text
  • image
  • video
output_modalities
  • text
capabilities
  • reasoning
  • structuredOutputs
  • toolCalling
  • videoInput
  • visionInput
  • webSearch

google ↗

source model id
Gemini 4 Argon
hosting
copilot-subscription
platforms
  • GitHub Copilot
architecture
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)

Gemini 4 Argon ↗

source model id
google/gemini-4-argon
hosting
third-party
platforms
  • Google Vertex AI
context length
1048576
max output tokens
65536
architecture
input_modalities
  • text
output_modalities
  • text
capabilities

    Gemini 4 Argon ↗

    source model id
    google/gemini-4-argon
    hosting
    vercel-gateway
    platforms
    • Vercel AI Gateway
    context length
    1000000
    max output tokens
    1000000
    architecture
    input_modalities
    • text
    • image
    • pdf
    • video
    output_modalities
    • text
    capabilities
    • promptCaching
    • reasoning
    • structuredOutputs
    • toolCalling
    • videoInput
    • visionInput
    • webSearch
    regions
    • eu
    • us

    Safety assessments

    1–1 / 1

    Foundation Model Transparency Index 2025 ↗

    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

    cloudflareWorkersAI ↗

    field
    context_length
    value
    1048576
    normalized value
    1048576
    scope
    source-model
    source id
    cloudflareWorkersAI
    confidence
    1

    openRouter ↗

    field
    context_length
    value
    1048576
    normalized value
    1048576
    scope
    source-model
    source id
    openRouter
    confidence
    1

    openRouter ↗

    field
    context_length
    value
    1048576
    normalized value
    1048576
    scope
    source-model
    source id
    openRouter
    confidence
    1

    vercelAIGatewayCatalog ↗

    field
    context_length
    value
    1000000
    normalized value
    1000000
    scope
    source-model
    source id
    vercelAIGatewayCatalog
    confidence
    1

    cloudflareWorkersAI ↗

    field
    max_output_tokens
    value
    65536
    normalized value
    65536
    scope
    source-model
    source id
    cloudflareWorkersAI
    confidence
    1

    openRouter ↗

    field
    max_output_tokens
    value
    943718
    normalized value
    943718
    scope
    source-model
    source id
    openRouter
    confidence
    1

    openRouter ↗

    field
    max_output_tokens
    value
    943718
    normalized value
    943718
    scope
    source-model
    source id
    openRouter
    confidence
    1

    vercelAIGatewayCatalog ↗

    field
    max_output_tokens
    value
    1000000
    normalized value
    1000000
    scope
    source-model
    source id
    vercelAIGatewayCatalog
    confidence
    1

    Original sources

    1–14 / 14

    Google · Model reference ↗

    OpenRouter · Model page ↗

    OpenRouter · Model page ↗

    Vercel AI Gateway · Model page ↗

    GitHub · Documentation ↗

    GitHub · Source snapshot ↗

    api.cheaperinference.com · Source snapshot ↗

    Cloudflare AI · Catalog ↗

    Epoch AI · Catalog ↗

    GitHub · Catalog ↗

    LMArena · Catalog ↗

    OpenRouter · Catalog ↗

    OpenRouter · Catalog ↗

    Vercel AI Gateway · Catalog ↗

    Source links

    1–10 / 10

    Explore more models

    Models

    Loading
    EVIDENCE / COMPARISON

    Benchmarks

    Explore every benchmark

    Loading

    These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

    Install TensorTrace