Model comparison

Gemini 3.7 Flash vs Gemini 3.8 Flash

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 59.8 on the Noometry Index.

Last verified . 44 shared benchmarks.

Gemini 3.7 Flash Google

59.8

Rank #14 Confirmed

Gemini 3.8 Flash Google

61.8

Rank #11 Confirmed

Summary

  • They share 44 benchmarks with published results for both. Gemini 3.7 Flash scores higher in 2 categories and Gemini 3.8 Flash in 8 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.8 Flash leads 76.9 to 70.0.
  • The biggest single-benchmark swing is FrontierMath Tier 4: 36.6% for Gemini 3.7 Flash and 22% for Gemini 3.8 Flash.
  • Both cost about the same: $0.75 input and $3.75 output per million tokens.

Side by side

Gemini 3.7 Flash and Gemini 3.8 Flash specifications
Gemini 3.7 FlashGemini 3.8 Flash
ProviderGoogleGoogle
Noometry Index59.861.8
Released2026-08-132026-09-02
WeightsProprietaryProprietary
Context window1.05M1.05M
Max output66K66K
Input $ / M tokens$0.75$0.75
Output $ / M tokens$3.75$3.75
Results tracked4450

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

Category by category

Coding Gemini 3.8 Flash leads

Gemini 3.7 Flash: 56.2 (#22), Gemini 3.8 Flash: 59.2 (#15)

Coding benchmarks
BenchmarkGemini 3.7 FlashGemini 3.8 Flash
DeepSWE65.5%73.8%
FrontierCode43.6%41.2%
LMArena WebDev15921584
FrontierSWE20.3%19.6%
SciCode59.8%56.6%
LMArena Coding14971510
ALE-Bench904.31,270
CursorBench—39.6%
WeirdML—84.8%

Agentic & Tool Use Too close to call

Gemini 3.7 Flash: 42.1 (#19), Gemini 3.8 Flash: 41.8 (#21)

Agentic & Tool Use benchmarks
BenchmarkGemini 3.7 FlashGemini 3.8 Flash
APEX-Agents67.8%64.3%
Remote Labor Index5%5.8%
GDP.pdf23.8%23.4%
Vending-Bench 2—5,094

Reasoning Gemini 3.8 Flash leads

Gemini 3.7 Flash: 70.0 (#15), Gemini 3.8 Flash: 76.9 (#5)

Reasoning benchmarks
BenchmarkGemini 3.7 FlashGemini 3.8 Flash
ARC-AGI-284.6%89.2%
NYT Connections (extended)94%97.4%
ARC-AGI-195.5%98.5%
CritPt14.3%18.3%
Chess Puzzles47%61%
LMArena Hard Prompts14941508
Mystery Game Puzzles37%47%
DTBench96.8%95.7%
LMCA50.4%52.9%
Epoch Capabilities Index157.27156.71
Surface Evolver Bench—76.9%

Math Gemini 3.7 Flash leads

Gemini 3.7 Flash: 69.6 (#23), Gemini 3.8 Flash: 65.3 (#28)

Math benchmarks
BenchmarkGemini 3.7 FlashGemini 3.8 Flash
FrontierMath (Tiers 1-3)71.6%68.4%
FrontierMath Tier 436.6%22%
OTIS Mock AIME 2024-202597.2%98.9%
ProofBench58%48%
LMArena Math15071528

Knowledge Gemini 3.8 Flash leads

Gemini 3.7 Flash: 69.7 (#5), Gemini 3.8 Flash: 74.8 (#2)

Knowledge benchmarks
BenchmarkGemini 3.7 FlashGemini 3.8 Flash
GPQA Diamond94.8%95.4%
SimpleQA Verified69.2%69.7%
LMArena Expert15081524
Humanity's Last Exam—44.5%

Multimodal Gemini 3.8 Flash leads

Gemini 3.7 Flash: 37.3 (#73), Gemini 3.8 Flash: 40.7 (#45)

Multimodal benchmarks
BenchmarkGemini 3.7 FlashGemini 3.8 Flash
LMArena Vision13161314
Furniture Assembly26.7%31.7%
Blueprint-Bench 2—38.6%

Multilingual Too close to call

Gemini 3.7 Flash: 57.6 (#7), Gemini 3.8 Flash: 58.0 (#5)

Multilingual benchmarks
BenchmarkGemini 3.7 FlashGemini 3.8 Flash
LMArena Non-English14841491
LMArena Chinese15481554
LMArena French15051498
LMArena German14981493
LMArena Japanese15121502
LMArena Korean14831459
LMArena Russian15161515
LMArena Spanish15031485

Instruction Following Too close to call

Gemini 3.7 Flash: 77.7 (#15), Gemini 3.8 Flash: 78.0 (#13)

Instruction Following benchmarks
BenchmarkGemini 3.7 FlashGemini 3.8 Flash
LMArena Instruction Following14831490

Long Context Too close to call

Gemini 3.7 Flash: 45.7 (#30), Gemini 3.8 Flash: 46.3 (#24)

Long Context benchmarks
BenchmarkGemini 3.7 FlashGemini 3.8 Flash
LMArena Longer Query14921508

Writing & Preference Gemini 3.8 Flash leads

Gemini 3.7 Flash: 71.2 (#20), Gemini 3.8 Flash: 72.2 (#15)

Writing & Preference benchmarks
BenchmarkGemini 3.7 FlashGemini 3.8 Flash
LMArena Text14861499
LMArena Creative Writing14901492
EQ-Bench Creative Writing17231748
LMArena Multi-Turn14891501

Frequently asked questions

Is Gemini 3.7 Flash better than Gemini 3.8 Flash?

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 59.8 on the Noometry Index.

Which is cheaper, Gemini 3.7 Flash or Gemini 3.8 Flash?

Gemini 3.8 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; Gemini 3.7 Flash lists at $0.75 and $3.75.

Is Gemini 3.7 Flash or Gemini 3.8 Flash better for coding?

Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 56.2 in the Noometry coding category.

Which has the bigger context window?

Both accept 1.05M tokens.

How many benchmarks do Gemini 3.7 Flash and Gemini 3.8 Flash share?

44 benchmarks have published results for both models. Gemini 3.7 Flash has 44 scored results on Noometry and Gemini 3.8 Flash has 50.

Related comparisons

Go deeper