Noometry

Google, proprietary

Gemini 3.7 Flash

Gemini 3.7 Flash by Google ranks 14th of 354 ranked models on the Noometry Index as of October 2026, with a score of 59.8. Its strongest category is knowledge, where it ranks 5th. 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
#14 of 354
Index score
59.8
Evidence
Confirmed 44 results
Provider
Google
Released
August 13, 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
#119 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 56.2
  2. Agentic & Tool Use 42.1
  3. Reasoning 70.0
  4. Math 69.6
  5. Knowledge 69.7
  6. Multimodal 37.3
  7. Multilingual 57.6
  8. Instruction Following 77.7
  9. Long Context 45.7
  10. Writing & Preference 71.2
CategoryScoreRankResults
Coding56.2#226
Agentic & Tool Use42.1#193
Reasoning70.0#159
Math69.6#235
Knowledge69.7#53
Multimodal37.3#732
Multilingual57.6#71
Instruction Following77.7#151
Long Context45.7#301
Writing & Preference71.2#204

Strengths and weaknesses

Categories where Gemini 3.7 Flash places highest and lowest among the models ranked in each, with its score against that category's median.

Strongest categories

CategoryScorevs medianRank
Knowledge69.7+32.4#5 of 314, top 2%
Multilingual57.6+10.2#7 of 297, top 3%
Reasoning70.0+46.4#15 of 350, top 5%

Weakest categories

CategoryScorevs medianRank
Multimodal37.3−1.2#73 of 128, top 58%
Agentic & Tool Use42.1+11.7#19 of 154, top 13%
Long Context45.7+4.8#30 of 296, top 11%

Closest competitors

The models ranked just above and below Gemini 3.7 Flash. When scores are this close, price and speed are often the better way to choose.

ModelRankScoreBlended $/MSpeed
Claude Sonnet 5.5#1061.9$4—Compare
Gemini 3.8 Flash#1161.8$1.50—Compare
GPT-6 Sol#1261.8$4—Compare
Claude Opus 4.8#1360.7$1034Compare
Kimi K3#1559.5$6—Compare
GPT-5.4#1659.4$5.6312Compare
GPT-5.6 Terra#1759.2$4.5011Compare
GPT-5.4 Pro#1858.9$67.50—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
DeepSWE65.3%highEpoch AI
DeepSWE53.8%lowEpoch AI
DeepSWE65.5%#15 of 29, top 52%mediumEpoch AI
FrontierCode43.6%#14 of 37, top 38%Epoch AI
LMArena WebDev1592#24 of 113, top 22%highLMArena2026-10-08
FrontierSWE20.3%#13 of 18, top 73%highEpoch AI
SciCode56.8%highEpoch AI
SciCode53.6%lowEpoch AI
SciCode59.8%#7 of 121, top 6%mediumEpoch AI
LMArena Coding1497#23 of 294, top 8%highLMArena2026-10-08
ALE-Bench904.3#50 of 105, top 48%highEpoch AI

Agentic & Tool Use

BenchmarkScorePositionSettingSourceDate
APEX-Agents67.8%#5 of 49, top 11%Epoch AI
Remote Labor Index5%#7 of 14, top 50%Epoch AI
GDP.pdf23.8%#13 of 36, top 37%highEpoch AI
GDP.pdf21.8%mediumEpoch AI

Reasoning

BenchmarkScorePositionSettingSourceDate
ARC-AGI-284.6%#11 of 83, top 14%highEpoch AI
ARC-AGI-252.9%lowEpoch AI
ARC-AGI-263.8%mediumEpoch AI
NYT Connections (extended)94%#8 of 91, top 9%Lech Mazur benchmarks
ARC-AGI-195.5%#13 of 83, top 16%highEpoch AI
ARC-AGI-185.2%lowEpoch AI
ARC-AGI-191.2%mediumEpoch AI
CritPt14.3%#39 of 134, top 30%highEpoch AI
CritPt5.7%lowEpoch AI
CritPt9.4%mediumEpoch AI
Chess Puzzles47%#14 of 129, top 11%highEpoch AI2026-08-14
LMArena Hard Prompts1494#14 of 297, top 5%highLMArena2026-10-08
Mystery Game Puzzles37%#15 of 74, top 21%highEpoch AI2026-08-14
DTBench96.8%#9 of 151, top 6%highEpoch AI
DTBench93.3%lowEpoch AI
DTBench94.7%mediumEpoch AI
LMCA50.4%#20 of 125, top 16%highEpoch AI
LMCA47.1%lowEpoch AI
LMCA49.2%mediumEpoch AI
Epoch Capabilities Index157.27#16 of 213, top 8%Epoch AI2026-08-13

Math

BenchmarkScorePositionSettingSourceDate
FrontierMath (Tiers 1-3)71.6%#23 of 81, top 29%highEpoch AI2026-08-14
FrontierMath Tier 436.6%#24 of 63, top 39%highEpoch AI2026-08-14
OTIS Mock AIME 2024-202597.2%#27 of 173, top 16%highEpoch AI2026-08-14
ProofBench58%#20 of 77, top 26%Epoch AI
LMArena Math1507#8 of 285, top 3%highLMArena2026-10-08

Knowledge

BenchmarkScorePositionSettingSourceDate
GPQA Diamond94.8%#5 of 186, top 3%highEpoch AI2026-08-14
SimpleQA Verified69.2%#9 of 77, top 12%highEpoch AI2026-08-27
LMArena Expert1508#16 of 273, top 6%highLMArena2026-10-08

Multimodal

BenchmarkScorePositionSettingSourceDate
LMArena Vision1316#6 of 122, top 5%highLMArena2026-10-09
Furniture Assembly26.7%#26 of 31, top 84%highEpoch AI2026-09-10

Multilingual

BenchmarkScorePositionSettingSourceDate
LMArena Non-English1484#7 of 297, top 3%highLMArena2026-10-08
LMArena Chinese1548#7 of 285, top 3%highLMArena2026-10-08
LMArena French1505#7 of 223, top 4%highLMArena2026-10-08
LMArena German1498#7 of 231, top 4%highLMArena2026-10-08
LMArena Japanese1512#3 of 211, top 2%highLMArena2026-10-08
LMArena Korean1483#5 of 213, top 3%highLMArena2026-10-08
LMArena Russian1516#4 of 283, top 2%highLMArena2026-10-08
LMArena Spanish1503#5 of 226, top 3%highLMArena2026-10-08

Instruction Following

BenchmarkScorePositionSettingSourceDate
LMArena Instruction Following1483#12 of 298, top 5%highLMArena2026-10-08

Long Context

BenchmarkScorePositionSettingSourceDate
LMArena Longer Query1492#12 of 291, top 5%highLMArena2026-10-08

Writing & Preference

BenchmarkScorePositionSettingSourceDate
LMArena Text1486#11 of 297, top 4%highLMArena2026-10-08
LMArena Creative Writing1490#8 of 295, top 3%highLMArena2026-10-08
EQ-Bench Creative Writing1723#29 of 115, top 26%EQ-Bench
LMArena Multi-Turn1489#10 of 295, top 4%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 3.7 Flash

Other Google models

Frequently asked questions

How good is Gemini 3.7 Flash?

Gemini 3.7 Flash by Google ranks 14th of 354 ranked models on the Noometry Index as of October 2026, with a score of 59.8. Its strongest category is knowledge, where it ranks 5th. 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 3.7 Flash cost?

Gemini 3.7 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 3.7 Flash's context window?

Gemini 3.7 Flash accepts up to 1.05M tokens of input and can write up to 66K tokens in one response.

Is Gemini 3.7 Flash open source?

No. Gemini 3.7 Flash is proprietary and available only through Google's API and partner platforms.

What are Gemini 3.7 Flash's strengths and weaknesses?

Relative to other ranked models, Gemini 3.7 Flash places best in knowledge, multilingual, reasoning and lowest in multimodal, agentic & tool use, long context.

What is Gemini 3.7 Flash best at?

Its best category is knowledge, where it ranks 5th on Noometry.