Noometry

Model comparison

Gemini 3.8 Flash vs Gemini 4 Argon

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 56.5 on the Noometry Index.

Last verified . 21 shared benchmarks.

Gemini 3.8 Flash Google

61.8

Rank #11 Confirmed

Gemini 4 Argon Google

56.5

Rank #24 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Gemini 3.8 Flash scores higher in 3 categories and Gemini 4 Argon in 7 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.8 Flash leads 76.9 to 44.2.
  • The biggest single-benchmark swing is ProofBench: 48% for Gemini 3.8 Flash and 99% for Gemini 4 Argon.

Side by side

Gemini 3.8 FlashGemini 4 Argon
ProviderGoogleGoogle
Noometry Index61.856.5
Released2026-09-022026-09-30
WeightsProprietaryProprietary
Context window1.05M—
Max output66K—
Input $ / M tokens$0.75—
Output $ / M tokens$3.75—
Results tracked5021

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

Category by category

Coding Gemini 4 Argon leads

Gemini 3.8 Flash: 59.2 (#15), Gemini 4 Argon: 62.0 (#9)

BenchmarkGemini 3.8 FlashGemini 4 Argon
LMArena WebDev15841678
FrontierSWE19.6%55%
SciCode56.6%61.8%
LMArena Coding15101550
DeepSWE73.8%—
FrontierCode41.2%—
CursorBench39.6%—
WeirdML84.8%—
ALE-Bench1,270—

Agentic & Tool Use Gemini 4 Argon leads

Gemini 3.8 Flash: 41.8 (#21), Gemini 4 Argon: 49.2 (#8)

BenchmarkGemini 3.8 FlashGemini 4 Argon
APEX-Agents64.3%82.2%
Vending-Bench 25,09413,718
Remote Labor Index5.8%—
GDP.pdf23.4%—

Reasoning Gemini 3.8 Flash leads

Gemini 3.8 Flash: 76.9 (#5), Gemini 4 Argon: 44.2 (#47)

BenchmarkGemini 3.8 FlashGemini 4 Argon
CritPt18.3%27.1%
LMArena Hard Prompts15081548
ARC-AGI-289.2%—
NYT Connections (extended)97.4%—
ARC-AGI-198.5%—
Chess Puzzles61%—
Mystery Game Puzzles47%—
DTBench95.7%—
LMCA52.9%—
Surface Evolver Bench76.9%—
Epoch Capabilities Index156.71—

Math Gemini 4 Argon leads

Gemini 3.8 Flash: 65.3 (#28), Gemini 4 Argon: 73.9 (#17)

BenchmarkGemini 3.8 FlashGemini 4 Argon
ProofBench48%99%
LMArena Math15281536
FrontierMath (Tiers 1-3)68.4%—
FrontierMath Tier 422%—
OTIS Mock AIME 2024-202598.9%—

Knowledge Gemini 3.8 Flash leads

Gemini 3.8 Flash: 74.8 (#2), Gemini 4 Argon: 43.9 (#89)

BenchmarkGemini 3.8 FlashGemini 4 Argon
LMArena Expert15241553
GPQA Diamond95.4%—
Humanity's Last Exam44.5%—
SimpleQA Verified69.7%—

Multimodal Gemini 4 Argon leads

Gemini 3.8 Flash: 40.7 (#45), Gemini 4 Argon: 46.5 (#14)

BenchmarkGemini 3.8 FlashGemini 4 Argon
Blueprint-Bench 238.6%54.4%
LMArena Vision1314—
Furniture Assembly31.7%—

Multilingual Gemini 4 Argon leads

Gemini 3.8 Flash: 58.0 (#5), Gemini 4 Argon: 60.3 (#1)

BenchmarkGemini 3.8 FlashGemini 4 Argon
LMArena Non-English14911523
LMArena Chinese15541610
LMArena Russian15151537
LMArena Spanish14851497
LMArena French1498—
LMArena German1493—
LMArena Japanese1502—
LMArena Korean1459—

Instruction Following Gemini 4 Argon leads

Gemini 3.8 Flash: 78.0 (#13), Gemini 4 Argon: 80.1 (#2)

BenchmarkGemini 3.8 FlashGemini 4 Argon
LMArena Instruction Following14901538

Long Context Gemini 4 Argon leads

Gemini 3.8 Flash: 46.3 (#24), Gemini 4 Argon: 47.6 (#15)

BenchmarkGemini 3.8 FlashGemini 4 Argon
LMArena Longer Query15081549

Writing & Preference Too close to call

Gemini 3.8 Flash: 72.2 (#15), Gemini 4 Argon: 71.4 (#19)

BenchmarkGemini 3.8 FlashGemini 4 Argon
LMArena Text14991534
LMArena Creative Writing14921531
LMArena Multi-Turn15011557
EQ-Bench Creative Writing1748—

Frequently asked questions

Is Gemini 3.8 Flash better than Gemini 4 Argon?

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 56.5 on the Noometry Index.

Is Gemini 3.8 Flash or Gemini 4 Argon better for coding?

Gemini 4 Argon scores higher on coding benchmarks: 62.0 versus 59.2 in the Noometry coding category.

How many benchmarks do Gemini 3.8 Flash and Gemini 4 Argon share?

21 benchmarks have published results for both models. Gemini 3.8 Flash has 50 scored results on Noometry and Gemini 4 Argon has 21.

Related comparisons

Go deeper