Google: Gemini 3.6 Flash

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and less he…

google/gemini-3.6-flash-20260721

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and less hedging, while reducing token use and the number of model calls needed to complete a task.

Specifications & capabilities

Input
text, image, video, file, audio
Output
text
Context window · tokens
1048576
Knowledge cutoff
2026-03
Published model ID
gemini-3.6-flash@default
Capabilities
audioInput, batch, computerUse, fileInput, multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, videoInput, visionInput, webSearch
Description source ↗

Evaluations

1–20 / 116

OpenRouter Benchmarks

93.013%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Google AI Studio
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
4
sample size
396
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
2
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
Google AI Studio
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-01T19:12:42.162Z
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
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
396
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.9301345
accuracy_std_dev
0.002525500000000014
cost_per_task_usd
0.044492378787878796
output_tokens_per_task
11715.780303030304
latency_seconds_per_task
69.1700404040404
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
12
benchmark_evaluation
true
openrouter_permaslug
google/gemini-3.6-flash-20260721
source model id
google/gemini-3.6-flash-20260721
Original result ↗

OpenRouter Benchmarks

73%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Google AI Studio
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
4
sample size
100
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
2
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 AI Studio
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-01T19:04:55.721Z
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
100
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.73
accuracy_std_dev
0.04333300000000001
cost_per_task_usd
0.24468226999999998
output_tokens_per_task
22552.35
latency_seconds_per_task
158.52406
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
10
benchmark_evaluation
true
openrouter_permaslug
google/gemini-3.6-flash-20260721
source model id
google/gemini-3.6-flash-20260721
Original result ↗

OpenRouter Benchmarks

93.35%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · Google
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
6
sample size
792
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
4
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
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
2026-10-01T19:12:42.153Z
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
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
792
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.9335015000000001
accuracy_std_dev
0.000841499999999995
cost_per_task_usd
0.04714142045454545
output_tokens_per_task
11818.68813131313
latency_seconds_per_task
67.6007297979798
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
40
benchmark_evaluation
true
openrouter_permaslug
google/gemini-3.6-flash-20260721
source model id
google/gemini-3.6-flash-20260721
Original result ↗

LMArena

1,512.303

source id
lmarena
leaderboard name
LMArena Text Style Control French
dimension
style
metric
Arena rating
rank
10
sample size
1138
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 3.6 Flash (High)
confidence lower
1493.5185948979436
confidence upper
1531.0866243223263
Original result ↗

OpenRouter Benchmarks

76.333%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · Google
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
10
sample size
200
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
4
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
2026-10-01T19:04:58.090Z
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
200
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.7633335
accuracy_std_dev
0.0033334999999999892
cost_per_task_usd
0.178977705
output_tokens_per_task
23034.1
latency_seconds_per_task
157.076125
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-3.6-flash-20260721
source model id
google/gemini-3.6-flash-20260721
Original result ↗

LMArena

1,510.114

source id
lmarena
leaderboard name
LMArena Text Factuality French
dimension
factuality
metric
Arena rating
rank
11
sample size
937
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 3.6 Flash (High)
confidence lower
1492.1623796286758
confidence upper
1528.0646327455188
Original result ↗

LMArena

1,502.602

source id
lmarena
leaderboard name
LMArena Text French
dimension
general
metric
Arena rating
rank
11
sample size
1138
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 3.6 Flash (High)
confidence lower
1483.8402747738035
confidence upper
1521.3630742960092
Original result ↗

LMArena

1,478.379

source id
lmarena
leaderboard name
LMArena Text Factuality Spanish
dimension
factuality
metric
Arena rating
rank
11
sample size
796
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 3.6 Flash (High)
confidence lower
1457.7004352052822
confidence upper
1499.05748444806
Original result ↗

OpenRouter Benchmarks

92.761%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · auto-routing
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
11
sample size
396
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
2
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
auto-routing
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-01T19:11:04.522Z
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
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
396
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.9276095000000001
accuracy_std_dev
0.005050500000000013
cost_per_task_usd
0.04436604545454545
output_tokens_per_task
11683.290404040405
latency_seconds_per_task
61.67028282828283
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
132
benchmark_evaluation
true
openrouter_permaslug
google/gemini-3.6-flash-20260721
source model id
google/gemini-3.6-flash-20260721
Original result ↗

LMArena

1,504.555

source id
lmarena
leaderboard name
LMArena Text Math
dimension
general
metric
Arena rating
rank
13
sample size
1707
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 3.6 Flash (High)
confidence lower
1490.2453524472605
confidence upper
1518.8642049015043
Original result ↗

LMArena

1,490.417

source id
lmarena
leaderboard name
LMArena Text Factuality Math
dimension
factuality
metric
Arena rating
rank
15
sample size
1502
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 3.6 Flash (High)
confidence lower
1476.6912293214716
confidence upper
1504.1419371325426
Original result ↗

LMArena

1,532.223

source id
lmarena
leaderboard name
LMArena Text Chinese
dimension
general
metric
Arena rating
rank
17
sample size
2592
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 3.6 Flash (High)
confidence lower
1520.1698690577325
confidence upper
1544.2754614186388
Original result ↗

LMArena

1,501.129

source id
lmarena
leaderboard name
LMArena Text Style Control Math
dimension
style
metric
Arena rating
rank
17
sample size
1707
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 3.6 Flash (High)
confidence lower
1486.8148909971142
confidence upper
1515.443536356328
Original result ↗

LMArena

1,470.768

source id
lmarena
leaderboard name
LMArena Text Style Control Creative Writing
dimension
style
metric
Arena rating
rank
18
sample size
7369
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 3.6 Flash (High)
confidence lower
1462.7211997498728
confidence upper
1478.8150726241279
Original result ↗

LMArena

1,309.476

source id
lmarena
leaderboard name
LMArena Vision Ocr
dimension
multimodal
metric
Arena rating
rank
18
sample size
7034
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 3.6 Flash (High)
confidence lower
1301.466095044878
confidence upper
1317.484930062986
Original result ↗

LMArena

1,298.367

source id
lmarena
leaderboard name
LMArena Vision Style Control Ocr
dimension
multimodal
metric
Arena rating
rank
19
sample size
7034
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 3.6 Flash (High)
confidence lower
1290.3178763411238
confidence upper
1306.4159732765117
Original result ↗

LMArena

1,480.89

source id
lmarena
leaderboard name
LMArena Text English
dimension
general
metric
Arena rating
rank
20
sample size
14908
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 3.6 Flash (High)
confidence lower
1475.0310929950622
confidence upper
1486.7483278749082
Original result ↗

LMArena

1,315.539

source id
lmarena
leaderboard name
LMArena Vision Diagram
dimension
multimodal
metric
Arena rating
rank
20
sample size
2630
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 3.6 Flash (High)
confidence lower
1303.3927859828118
confidence upper
1327.6858656565696
Original result ↗

LMArena

1,296.693

source id
lmarena
leaderboard name
LMArena Vision Overall
dimension
multimodal
metric
Arena rating
rank
20
sample size
10352
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 3.6 Flash (High)
confidence lower
1289.1719178215487
confidence upper
1304.2137007216566
Original result ↗

LMArena

1,487.06

source id
lmarena
leaderboard name
LMArena Text Russian
dimension
general
metric
Arena rating
rank
21
sample size
4084
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemini 3.6 Flash (High)
confidence lower
1477.289511922584
confidence upper
1496.829607130431
Original result ↗

Published prices

41–46 / 46

google/gemini-3.6-flash ↗

$1.88

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
output_tokens_per_million
Currency
USD
Billing conditions
model_type
language
quote_scope
gateway_catalog
service_tier
flex
billing_scope
Vercel public catalog; endpoint prices may differ
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

google/gemini-3.6-flash ↗

$6.75

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
output_tokens_per_million
Currency
USD
Billing conditions
model_type
language
quote_scope
gateway_catalog
service_tier
priority
billing_scope
Vercel public catalog; endpoint prices may differ
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

google/gemini-3.6-flash ↗

$4.13

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
output_tokens_per_million
Currency
USD
Billing conditions
region
eu
model_type
language
quote_scope
gateway_catalog
billing_scope
Vercel public catalog; endpoint prices may differ
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

google/gemini-3.6-flash ↗

$4.13

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
output_tokens_per_million
Currency
USD
Billing conditions
region
us
model_type
language
quote_scope
gateway_catalog
billing_scope
Vercel public catalog; endpoint prices may differ
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

google/gemini-3.6-flash ↗

$14.00

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
request
Currency
USD
Billing conditions
charge
maps_search
model_type
language
quote_scope
gateway_catalog
billing_scope
Vercel public catalog; endpoint prices may differ
Billing label
Maps search
Pricing via
Vercel AI Gateway

google/gemini-3.6-flash ↗

$0.01

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
request
Currency
USD
Billing conditions
charge
web_search
model_type
language
quote_scope
gateway_catalog
billing_scope
Vercel public catalog; endpoint prices may differ
Billing label
Web search
Pricing via
Vercel AI Gateway

Provider specifications & access

1–4 / 4

gemini-3.6-flash ↗

source model id
gemini-3.6-flash
hosting
gateway
platforms
  • Cheaper Inference
context length
1000000
max output tokens
65536
architecture
input_modalities
  • text
  • image
  • video
output_modalities
  • text
capabilities
  • reasoning
  • structuredOutputs
  • toolCalling
  • videoInput
  • visionInput
  • webSearch

Gemini 3.6 Flash ↗

source model id
google/gemini-3.6-flash
hosting
third-party
platforms
  • Google Vertex AI
context length
1048576
max output tokens
65536
architecture
input_modalities
  • text
output_modalities
  • text
capabilities
  • reasoning

Gemini 3.6 Flash ↗

source model id
google/gemini-3.6-flash
hosting
vercel-gateway
platforms
  • Vercel AI Gateway
context length
1000000
max output tokens
64000
architecture
input_modalities
  • text
  • image
  • pdf
  • video
output_modalities
  • text
capabilities
  • promptCaching
  • reasoning
  • structuredOutputs
  • toolCalling
  • videoInput
  • visionInput
  • webSearch
regions
  • eu
  • us

Gemini 3.6 Flash ↗

source model id
publishers/google/models/gemini-3.6-flash@default
hosting
vertex-managed
platforms
  • Google Cloud Vertex AI
context length
1048576
max output tokens
65536
architecture
input_modalities
  • audio
  • image
  • text
  • video
output_modalities
  • text
capabilities
  • batch
  • computerUse
  • multimodal
  • promptCaching
  • reasoning
  • structuredOutputs
  • toolCalling
  • visionInput

Safety assessments

1–1 / 1

Foundation Model Transparency Index 2025 ↗

41 / 100

source id
stanfordFMTI
canonical model id
google/gemini-3.6-flash-20260721
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

1–11 / 11

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

vertexAI ↗

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

vercelAIGatewayCatalog ↗

field
knowledge_cutoff
reported field
knowledge_cutoff
value
2026-03
normalized value
2026-03
precision
month
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
65536
normalized value
65536
scope
source-model
source id
openRouter
confidence
1

openRouter ↗

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

vercelAIGatewayCatalog ↗

field
max_output_tokens
value
64000
normalized value
64000
scope
source-model
source id
vercelAIGatewayCatalog
confidence
1

vertexAI ↗

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

Original sources

1–16 / 16

Google · Model reference ↗

Google Cloud · Model page ↗

OpenRouter · Model page ↗

OpenRouter · Model page ↗

Vercel AI Gateway · Model page ↗

Google Cloud · Documentation ↗

GitHub · Source snapshot ↗

api.cheaperinference.com · Source snapshot ↗

Cloudflare AI · Catalog ↗

Epoch AI · Catalog ↗

GitHub · Catalog ↗

Google Cloud · 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