Noometry

Google, proprietary

Gemini 3.6 Flash

Gemini 3.6 Flash by Google ranks 33rd of 354 ranked models on the Noometry Index as of October 2026, with a score of 54.1. Its strongest category is knowledge, where it ranks 8th. API pricing starts at $0.75 per million input tokens and $3.75 per million output tokens, with a 1.05M-token context window.

Last verified

Noometry rank
#33 of 354
Index score
54.1
Evidence
Confirmed 46 results
Provider
Google
Released
July 21, 2026
Weights
Proprietary
Reasoning
Yes
Context window
1.05M
Max output
66K
Input price
$0.75 / M
Output price
$3.75 / M
Blended price
$1.50 / M
Output speed
Not measured
Value
#125 of 219
Knowledge cutoff
March 2026
Input
text, image, video, audio, pdf

Category scores

Each category score combines every public result we have in that category.

  1. Coding 50.0
  2. Agentic & Tool Use 32.3
  3. Reasoning 58.8
  4. Math 57.3
  5. Knowledge 67.8
  6. Multimodal 38.5
  7. Multilingual 56.5
  8. Instruction Following 77.0
  9. Long Context 45.1
  10. Writing & Preference 68.2
CategoryScoreRankResults
Coding50.0#486
Agentic & Tool Use32.3#652
Reasoning58.8#229
Math57.3#406
Knowledge67.8#83
Multimodal38.5#643
Multilingual56.5#191
Instruction Following77.0#331
Long Context45.1#501
Writing & Preference68.2#274

Strengths and weaknesses

Categories where Gemini 3.6 Flash places highest and lowest among the models ranked in each, with its score against that category's median.

Strongest categories

CategoryScorevs medianRank
Knowledge67.8+30.5#8 of 314, top 3%
Reasoning58.8+35.2#22 of 350, top 7%
Multilingual56.5+9.1#19 of 297, top 7%

Weakest categories

CategoryScorevs medianRank
Multimodal38.5−0.0#64 of 128, top 50%
Agentic & Tool Use32.3+2.0#65 of 154, top 43%
Long Context45.1+4.2#50 of 296, top 17%

Closest competitors

The models ranked just above and below Gemini 3.6 Flash. When scores are this close, price and speed are often the better way to choose.

ModelRankScoreBlended $/MSpeed
Claude Sonnet 5#2954.6$4—Compare
GPT-5.6 Luna#3054.6$0.4512Compare
DeepSeek V4 Pro#3154.3$0.9916Compare
Gemini 3.5 Flash#3254.2$3.38—Compare
GPT-5.2#3454.1$4.8115Compare
DeepSeek V4 Flash#3553.6$0.266Compare
GPT-6 Luna#3653.3$0.20—Compare
Grok 4.7#3753.1$3—Compare

Sponsored placements are available on pages like this one. Advertise on Noometry

Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

Coding

BenchmarkScorePositionSettingSourceDate
DeepSWE46.7%#24 of 29, top 83%highEpoch AI
FrontierCode34.4%#24 of 37, top 65%Epoch AI
LMArena WebDev1538#38 of 113, top 34%highLMArena2026-10-08
SciCode52.7%#35 of 121, top 29%highEpoch AI
WeirdML56.1%#37 of 119, top 32%highEpoch AI
LMArena Coding1491#29 of 294, top 10%highLMArena2026-10-08
ALE-Bench715.52#69 of 105, top 66%highEpoch AI

Agentic & Tool Use

BenchmarkScorePositionSettingSourceDate
APEX-Agents46.9%#30 of 49, top 62%Epoch AI
GDP.pdf14%#29 of 36, top 81%Epoch AI
GDP.pdf14%highEpoch AI

Reasoning

BenchmarkScorePositionSettingSourceDate
ARC-AGI-260.4%#28 of 83, top 34%highEpoch AI
ARC-AGI-230.4%lowEpoch AI
ARC-AGI-250.4%mediumEpoch AI
ARC-AGI-22.6%minimalEpoch AI
NYT Connections (extended)89%#22 of 91, top 25%Lech Mazur benchmarks
ARC-AGI-191.2%#23 of 83, top 28%highEpoch AI
ARC-AGI-176.5%lowEpoch AI
ARC-AGI-183.2%mediumEpoch AI
ARC-AGI-134.5%minimalEpoch AI
CritPt10.6%#46 of 134, top 35%highEpoch AI
Chess Puzzles40%highEpoch AI2026-08-02
Chess Puzzles43%#16 of 129, top 13%lowEpoch AI2026-08-07
Chess Puzzles35%minimalEpoch AI2026-08-07
LMArena Hard Prompts1485#23 of 297, top 8%highLMArena2026-10-08
Mystery Game Puzzles30%#27 of 74, top 37%highEpoch AI2026-08-05
Mystery Game Puzzles23%lowEpoch AI2026-08-05
Mystery Game Puzzles25%minimalEpoch AI2026-08-05
DTBench95.5%#17 of 151, top 12%highEpoch AI
LMCA44.9%#34 of 125, top 28%highEpoch AI
Epoch Capabilities Index154.25#36 of 213, top 17%Epoch AI2026-07-21

Math

BenchmarkScorePositionSettingSourceDate
FrontierMath (Tiers 1-3)58.9%#37 of 81, top 46%highEpoch AI2026-08-02
FrontierMath Tier 422%#40 of 63, top 64%highEpoch AI2026-08-02
MathArena Final-Answer Competitions70.8%#13 of 29, top 45%MathArena
OTIS Mock AIME 2024-202594.2%#39 of 173, top 23%highEpoch AI2026-08-02
OTIS Mock AIME 2024-202582.2%lowEpoch AI2026-08-07
OTIS Mock AIME 2024-202580%minimalEpoch AI2026-08-07
ProofBench36%#38 of 77, top 50%Epoch AI
LMArena Math1505#10 of 285, top 4%highLMArena2026-10-08

Knowledge

BenchmarkScorePositionSettingSourceDate
GPQA Diamond94.1%#9 of 186, top 5%highEpoch AI2026-08-02
GPQA Diamond86.4%lowEpoch AI2026-08-06
GPQA Diamond85.9%minimalEpoch AI2026-08-07
SimpleQA Verified66.2%#12 of 77, top 16%highEpoch AI2026-08-27
LMArena Expert1488#33 of 273, top 13%highLMArena2026-10-08

Multimodal

BenchmarkScorePositionSettingSourceDate
LMArena Vision1298#16 of 122, top 14%highLMArena2026-10-09
Blueprint-Bench 231.2%#13 of 31, top 42%Epoch AI
Furniture Assembly23.3%#27 of 31, top 88%highEpoch AI2026-09-10
LMArena Document1456#19 of 38, top 50%highLMArena2026-09-13

Multilingual

BenchmarkScorePositionSettingSourceDate
LMArena Non-English1469#19 of 297, top 7%highLMArena2026-10-08
LMArena Chinese1531#13 of 285, top 5%highLMArena2026-10-08
LMArena French1504#9 of 223, top 5%highLMArena2026-10-08
LMArena German1478#21 of 231, top 10%highLMArena2026-10-08
LMArena Japanese1476#15 of 211, top 8%highLMArena2026-10-08
LMArena Korean1431#29 of 213, top 14%highLMArena2026-10-08
LMArena Russian1487#14 of 283, top 5%highLMArena2026-10-08
LMArena Spanish1475#16 of 226, top 8%highLMArena2026-10-08

Instruction Following

BenchmarkScorePositionSettingSourceDate
LMArena Instruction Following1466#29 of 298, top 10%highLMArena2026-10-08

Long Context

BenchmarkScorePositionSettingSourceDate
LMArena Longer Query1474#31 of 291, top 11%highLMArena2026-10-08

Writing & Preference

BenchmarkScorePositionSettingSourceDate
LMArena Text1479#17 of 297, top 6%highLMArena2026-10-08
LMArena Creative Writing1465#15 of 295, top 6%highLMArena2026-10-08
EQ-Bench Creative Writing1604#41 of 115, top 36%EQ-Bench
LMArena Multi-Turn1481#20 of 295, top 7%highLMArena2026-10-08

API pricing by provider

RouteInput $/MOutput $/MCached input $/MChecked
google$0.75$3.75$0.0752026-10-10
openrouter$0.75$3.75$0.0752026-10-10
vertex$0.75$3.75$0.0752026-10-10

All Google API prices → Estimate your cost →

Compare Gemini 3.6 Flash

Other Google models

Frequently asked questions

How good is Gemini 3.6 Flash?

Gemini 3.6 Flash by Google ranks 33rd of 354 ranked models on the Noometry Index as of October 2026, with a score of 54.1. Its strongest category is knowledge, where it ranks 8th. API pricing starts at $0.75 per million input tokens and $3.75 per million output tokens, with a 1.05M-token context window.

How much does Gemini 3.6 Flash cost?

Gemini 3.6 Flash costs $0.75 per million input tokens and $3.75 per million output tokens on Google's own API, with cached input at $0.075.

What is Gemini 3.6 Flash's context window?

Gemini 3.6 Flash accepts up to 1.05M tokens of input and can write up to 66K tokens in one response.

Is Gemini 3.6 Flash open source?

No. Gemini 3.6 Flash is proprietary and available only through Google's API and partner platforms.

What are Gemini 3.6 Flash's strengths and weaknesses?

Relative to other ranked models, Gemini 3.6 Flash places best in knowledge, reasoning, multilingual and lowest in multimodal, agentic & tool use, long context.

What is Gemini 3.6 Flash best at?

Its best category is knowledge, where it ranks 8th on Noometry.