Noometry

Google, proprietary

Gemini 3.8 Flash

Gemini 3.8 Flash by Google ranks 11th of 354 ranked models on the Noometry Index as of October 2026, with a score of 61.8. Its strongest category is knowledge, where it ranks 2nd. 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
#11 of 354
Index score
61.8
Evidence
Confirmed 50 results
Provider
Google
Released
September 2, 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
#115 of 219
Knowledge cutoff
Unknown
Input
text, image, video, audio, pdf

Category scores

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

  1. Coding 59.2
  2. Agentic & Tool Use 41.8
  3. Reasoning 76.9
  4. Math 65.3
  5. Knowledge 74.8
  6. Multimodal 40.7
  7. Multilingual 58.0
  8. Instruction Following 78.0
  9. Long Context 46.3
  10. Writing & Preference 72.2
CategoryScoreRankResults
Coding59.2#158
Agentic & Tool Use41.8#213
Reasoning76.9#510
Math65.3#285
Knowledge74.8#24
Multimodal40.7#453
Multilingual58.0#51
Instruction Following78.0#131
Long Context46.3#241
Writing & Preference72.2#154

Strengths and weaknesses

Categories where Gemini 3.8 Flash places highest and lowest among the models ranked in each, with its score against that category's median.

Strongest categories

CategoryScorevs medianRank
Knowledge74.8+37.5#2 of 314, top 1%
Reasoning76.9+53.3#5 of 350, top 2%
Multilingual58.0+10.6#5 of 297, top 2%

Weakest categories

CategoryScorevs medianRank
Multimodal40.7+2.2#45 of 128, top 36%
Agentic & Tool Use41.8+11.4#21 of 154, top 14%
Math65.3+28.8#28 of 327, top 9%

Closest competitors

The models ranked just above and below Gemini 3.8 Flash. When scores are this close, price and speed are often the better way to choose.

ModelRankScoreBlended $/MSpeed
GPT-5.6 Sol#765.0$810Compare
GPT-5.5 Pro#864.3$67.50—Compare
GPT-5.5#963.4$11.2525Compare
Claude Sonnet 5.5#1061.9$4—Compare
GPT-6 Sol#1261.8$4—Compare
Claude Opus 4.8#1360.7$1034Compare
Gemini 3.7 Flash#1459.8$1.50—Compare
Kimi K3#1559.5$6—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
DeepSWE73.8%#3 of 29, top 11%highEpoch AI
DeepSWE71%mediumEpoch AI
FrontierCode41.2%#20 of 37, top 55%mediumEpoch AI
CursorBench39.6%#11 of 14, top 79%highEpoch AI
CursorBench37.3%mediumEpoch AI
LMArena WebDev1584#26 of 113, top 24%highLMArena2026-10-08
FrontierSWE19.6%#14 of 18, top 78%highEpoch AI
SciCode56.6%#17 of 121, top 15%highEpoch AI
SciCode54.3%lowEpoch AI
SciCode54.4%mediumEpoch AI
WeirdML84.8%#7 of 119, top 6%highEpoch AI
LMArena Coding1510#11 of 294, top 4%highLMArena2026-10-08
ALE-Bench1,270#28 of 105, top 27%highEpoch AI

Agentic & Tool Use

BenchmarkScorePositionSettingSourceDate
APEX-Agents64.3%#9 of 49, top 19%Epoch AI
Remote Labor Index5.8%#6 of 14, top 43%Epoch AI
GDP.pdf23.2%highEpoch AI
GDP.pdf23.4%#14 of 36, top 39%mediumEpoch AI
Vending-Bench 25,094#29 of 60, top 49%Epoch AI

Reasoning

BenchmarkScorePositionSettingSourceDate
ARC-AGI-289.2%#9 of 83, top 11%highEpoch AI
ARC-AGI-277.5%lowEpoch AI
ARC-AGI-282.9%mediumEpoch AI
NYT Connections (extended)97.4%#3 of 91, top 4%high reasoningLech Mazur benchmarks
ARC-AGI-198.5%#3 of 83, top 4%highEpoch AI
ARC-AGI-190.5%lowEpoch AI
ARC-AGI-197.5%mediumEpoch AI
CritPt18.3%#28 of 134, top 21%highEpoch AI
CritPt4%lowEpoch AI
CritPt12.3%mediumEpoch AI
Chess Puzzles61%#4 of 129, top 4%highEpoch AI2026-09-02
LMArena Hard Prompts1508#7 of 297, top 3%highLMArena2026-10-08
Mystery Game Puzzles47%#11 of 74, top 15%highEpoch AI2026-09-02
DTBench95.7%#16 of 151, top 11%Epoch AI
DTBench94.9%lowEpoch AI
DTBench94.9%mediumEpoch AI
LMCA51.5%Epoch AI
LMCA51.2%lowEpoch AI
LMCA52.9%#16 of 125, top 13%mediumEpoch AI
Surface Evolver Bench76.9%#7 of 25, top 29%highEpoch AI
Epoch Capabilities Index156.71#20 of 213, top 10%Epoch AI2026-09-02

Math

BenchmarkScorePositionSettingSourceDate
FrontierMath (Tiers 1-3)68.4%#26 of 81, top 33%highEpoch AI2026-09-02
FrontierMath Tier 422%#41 of 63, top 66%highEpoch AI2026-09-02
OTIS Mock AIME 2024-202598.9%#17 of 173, top 10%highEpoch AI2026-09-02
ProofBench48%#32 of 77, top 42%Epoch AI
LMArena Math1528#3 of 285, top 2%highLMArena2026-10-08

Knowledge

BenchmarkScorePositionSettingSourceDate
GPQA Diamond95.4%#3 of 186, top 2%highEpoch AI2026-09-02
Humanity's Last Exam44.5%#4 of 41, top 10%Epoch AI
SimpleQA Verified69.7%#7 of 77, top 10%highEpoch AI2026-09-02
LMArena Expert1524#9 of 273, top 4%highLMArena2026-10-08

Multimodal

BenchmarkScorePositionSettingSourceDate
LMArena Vision1314#8 of 122, top 7%highLMArena2026-10-09
Blueprint-Bench 238.6%#6 of 31, top 20%Epoch AI
Furniture Assembly31.7%#22 of 31, top 71%highEpoch AI2026-09-10

Multilingual

BenchmarkScorePositionSettingSourceDate
LMArena Non-English1491#5 of 297, top 2%highLMArena2026-10-08
LMArena Chinese1554#5 of 285, top 2%highLMArena2026-10-08
LMArena French1498#13 of 223, top 6%highLMArena2026-10-08
LMArena German1493#11 of 231, top 5%highLMArena2026-10-08
LMArena Japanese1502#6 of 211, top 3%highLMArena2026-10-08
LMArena Korean1459#12 of 213, top 6%highLMArena2026-10-08
LMArena Russian1515#5 of 283, top 2%highLMArena2026-10-08
LMArena Spanish1485#12 of 226, top 6%highLMArena2026-10-08

Instruction Following

BenchmarkScorePositionSettingSourceDate
LMArena Instruction Following1490#10 of 298, top 4%highLMArena2026-10-08

Long Context

BenchmarkScorePositionSettingSourceDate
LMArena Longer Query1508#7 of 291, top 3%highLMArena2026-10-08

Writing & Preference

BenchmarkScorePositionSettingSourceDate
LMArena Text1499#6 of 297, top 3%highLMArena2026-10-08
LMArena Creative Writing1492#6 of 295, top 3%highLMArena2026-10-08
EQ-Bench Creative Writing1748#27 of 115, top 24%EQ-Bench
LMArena Multi-Turn1501#5 of 295, top 2%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 3.8 Flash

Other Google models

Frequently asked questions

How good is Gemini 3.8 Flash?

Gemini 3.8 Flash by Google ranks 11th of 354 ranked models on the Noometry Index as of October 2026, with a score of 61.8. Its strongest category is knowledge, where it ranks 2nd. 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 3.8 Flash cost?

Gemini 3.8 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 3.8 Flash's context window?

Gemini 3.8 Flash accepts up to 1.05M tokens of input and can write up to 66K tokens in one response.

Is Gemini 3.8 Flash open source?

No. Gemini 3.8 Flash is proprietary and available only through Google's API and partner platforms.

What are Gemini 3.8 Flash's strengths and weaknesses?

Relative to other ranked models, Gemini 3.8 Flash places best in knowledge, reasoning, multilingual and lowest in multimodal, agentic & tool use, math.

What is Gemini 3.8 Flash best at?

Its best category is knowledge, where it ranks 2nd on Noometry.