Model comparison

Gemini 3.6 Flash vs Gemma 4 31B IT

Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 43.2 on the Noometry Index. Gemma 4 31B IT costs 9.8× less per token, which makes it the better buy when Gemini 3.6 Flash's lead doesn't matter for your workload.

Last verified . 30 shared benchmarks.

Gemini 3.6 Flash Google

54.1

Rank #30 Confirmed

Gemma 4 31B IT Google

43.2

Rank #85 Confirmed

Summary

  • They share 30 benchmarks with published results for both. Gemini 3.6 Flash scores higher in 8 categories and Gemma 4 31B IT in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.6 Flash leads 58.9 to 26.4.
  • The biggest single-benchmark swing is SimpleQA Verified: 66.2% for Gemini 3.6 Flash and 10.4% for Gemma 4 31B IT.
  • Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.6 Flash.
  • Gemini 3.6 Flash accepts more context: 1.05M tokens versus 262K.
  • Gemma 4 31B IT has downloadable open weights; the other is API-only.

Side by side

Gemini 3.6 Flash and Gemma 4 31B IT specifications
Gemini 3.6 FlashGemma 4 31B IT
ProviderGoogleGoogle
Noometry Index54.143.2
Released2026-07-212026-04-02
WeightsProprietaryOpen
Context window1.05M262K
Max output66K33K
Input $ / M tokens$0.75$0.09
Output $ / M tokens$3.75$0.34
Results tracked4635

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

Category by category

Coding Gemini 3.6 Flash leads

Gemini 3.6 Flash: 49.6 (#45), Gemma 4 31B IT: 41.9 (#98)

Coding benchmarks
BenchmarkGemini 3.6 FlashGemma 4 31B IT
LMArena WebDev15361364
SciCode52.7%43.4%
WeirdML56.1%52.3%
LMArena Coding14921459
ALE-Bench715.52925.5
DeepSWE46.7%—
FrontierCode34.4%—

Agentic & Tool Use Not comparable

Gemini 3.6 Flash: 32.4 (#56), Gemma 4 31B IT: —

Agentic & Tool Use benchmarks
BenchmarkGemini 3.6 FlashGemma 4 31B IT
APEX-Agents46.9%—
GDP.pdf14%—

Reasoning Gemini 3.6 Flash leads

Gemini 3.6 Flash: 58.9 (#20), Gemma 4 31B IT: 26.4 (#119)

Reasoning benchmarks
BenchmarkGemini 3.6 FlashGemma 4 31B IT
NYT Connections (extended)89%70.6%
CritPt10.6%1.4%
Chess Puzzles43%5%
LMArena Hard Prompts14861448
DTBench95.5%82.7%
LMCA44.9%39.3%
Epoch Capabilities Index154.36142.74
ARC-AGI-260.4%—
Kagi LLM Benchmark—63.5%
ARC-AGI-191.2%—
Thematic Generalization—53%
Mystery Game Puzzles30%—
Surface Evolver Bench—30.6%

Math Gemini 3.6 Flash leads

Gemini 3.6 Flash: 57.0 (#33), Gemma 4 31B IT: 41.3 (#72)

Math benchmarks
BenchmarkGemini 3.6 FlashGemma 4 31B IT
OTIS Mock AIME 2024-202594.2%73.3%
LMArena Math15041464
FrontierMath (Tiers 1-3)58.9%—
FrontierMath Tier 422%—
MathArena Final-Answer Competitions70.8%—
ProofBench36%—

Knowledge Gemini 3.6 Flash leads

Gemini 3.6 Flash: 67.8 (#7), Gemma 4 31B IT: 37.9 (#141)

Knowledge benchmarks
BenchmarkGemini 3.6 FlashGemma 4 31B IT
GPQA Diamond94.1%75.8%
SimpleQA Verified66.2%10.4%
LMArena Expert14891465
Vectara Hallucination Rate—7.4%

Multimodal Gemma 4 31B IT leads

Gemini 3.6 Flash: 38.7 (#55), Gemma 4 31B IT: 41.0 (#32)

Multimodal benchmarks
BenchmarkGemini 3.6 FlashGemma 4 31B IT
LMArena Vision12971278
LMArena Document14561425
Blueprint-Bench 231.2%—
Furniture Assembly23.3%—

Multilingual Gemini 3.6 Flash leads

Gemini 3.6 Flash: 56.8 (#17), Gemma 4 31B IT: 54.0 (#52)

Multilingual benchmarks
BenchmarkGemini 3.6 FlashGemma 4 31B IT
LMArena Non-English14701431
LMArena Chinese15301478
LMArena French15011436
LMArena Russian14901462
LMArena Spanish14771443
LMArena German1478—
LMArena Japanese1477—
LMArena Korean1435—

Instruction Following Gemini 3.6 Flash leads

Gemini 3.6 Flash: 77.2 (#27), Gemma 4 31B IT: 75.6 (#58)

Instruction Following benchmarks
BenchmarkGemini 3.6 FlashGemma 4 31B IT
LMArena Instruction Following14671433

Long Context Too close to call

Gemini 3.6 Flash: 45.1 (#47), Gemma 4 31B IT: 44.2 (#67)

Long Context benchmarks
BenchmarkGemini 3.6 FlashGemma 4 31B IT
LMArena Longer Query14751446

Writing & Preference Gemini 3.6 Flash leads

Gemini 3.6 Flash: 68.3 (#26), Gemma 4 31B IT: 60.7 (#92)

Writing & Preference benchmarks
BenchmarkGemini 3.6 FlashGemma 4 31B IT
LMArena Text14781443
LMArena Creative Writing14641416
EQ-Bench Creative Writing16041368
LMArena Multi-Turn14811452
EQ-Bench 4—1120

Frequently asked questions

Is Gemini 3.6 Flash better than Gemma 4 31B IT?

Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 43.2 on the Noometry Index. Gemma 4 31B IT costs 9.8× less per token, which makes it the better buy when Gemini 3.6 Flash's lead doesn't matter for your workload.

Which is cheaper, Gemini 3.6 Flash or Gemma 4 31B IT?

Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; Gemini 3.6 Flash lists at $0.75 and $3.75.

Is Gemini 3.6 Flash or Gemma 4 31B IT better for coding?

Gemini 3.6 Flash scores higher on coding benchmarks: 49.6 versus 41.9 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.6 Flash does, with 1.05M tokens against 262K.

How many benchmarks do Gemini 3.6 Flash and Gemma 4 31B IT share?

30 benchmarks have published results for both models. Gemini 3.6 Flash has 46 scored results on Noometry and Gemma 4 31B IT has 35.

Related comparisons

Go deeper