Noometry

Model comparison

Gemini 3.1 Pro Preview vs Gemma 4 26B A4B IT

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 43.5 on the Noometry Index. Gemma 4 26B A4B IT costs 32× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

Last verified . 28 shared benchmarks.

Gemini 3.1 Pro Preview Google

56.7

Rank #23 Confirmed

Gemma 4 26B A4B IT Google

43.5

Rank #92 Confirmed

Summary

  • They share 28 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 8 categories and Gemma 4 26B A4B IT in 1 category; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 21.8.
  • The biggest single-benchmark swing is Chess Puzzles: 55% for Gemini 3.1 Pro Preview and 6% for Gemma 4 26B A4B IT.
  • Gemma 4 26B A4B IT is cheaper at $0.09 / $0.30 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.
  • Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 262K.
  • Gemma 4 26B A4B IT has downloadable open weights; the other is API-only.

Side by side

Gemini 3.1 Pro PreviewGemma 4 26B A4B IT
ProviderGoogleGoogle
Noometry Index56.743.5
Released2026-02-192026-04-02
WeightsProprietaryOpen
Context window1.05M262K
Max output66K33K
Input $ / M tokens$2$0.09
Output $ / M tokens$12$0.30
Results tracked7128

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

Category by category

Coding Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 42.5 (#99), Gemma 4 26B A4B IT: 39.0 (#164)

BenchmarkGemini 3.1 Pro PreviewGemma 4 26B A4B IT
LMArena WebDev14471359
SciCode58.9%40%
WeirdML72.1%35.2%
LMArena Coding14841447
ALE-Bench1,161927.17
SWE-bench Verified75.6%—
DeepSWE11.7%—
GSO22.6%—
MirrorCode8.9%—
AlgoTune2.02—

Agentic & Tool Use Not comparable

Gemini 3.1 Pro Preview: 37.7 (#34), Gemma 4 26B A4B IT: —

BenchmarkGemini 3.1 Pro PreviewGemma 4 26B A4B IT
Terminal-Bench80.2%—
APEX-Agents35.3%—
τ²-bench Banking26%—
DeepResearch Bench47.8%—
PostTrainBench22%—
BALROG57%—
ExploitBench26.1%—
GBAEval0.8%—
GDP.pdf17%—
LMArena Search1211—
METR Time Horizons77%—
Vending-Bench 23,774—

Reasoning Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.7 (#12), Gemma 4 26B A4B IT: 21.8 (#213)

BenchmarkGemini 3.1 Pro PreviewGemma 4 26B A4B IT
CritPt17.7%0%
Chess Puzzles55%6%
LMArena Hard Prompts14851439
DTBench97.1%74.9%
LMCA53.8%29.7%
Epoch Capabilities Index154.77141.85
ARC-AGI-277.1%—
SimpleBench79.6%—
NYT Connections (extended)97.4%—
ARC-AGI-198%—
EnigmaEval36.8%—
Thematic Generalization79.4%—
EBR-Bench14.3%—
Mystery Game Puzzles34%—
ForecastBench59—

Math Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 62.1 (#34), Gemma 4 26B A4B IT: 47.6 (#67)

BenchmarkGemini 3.1 Pro PreviewGemma 4 26B A4B IT
OTIS Mock AIME 2024-202595.6%82.2%
LMArena Math14851470
FrontierMath (Tiers 1-3)59.6%—
FrontierMath Tier 426.8%—
MathArena Final-Answer Competitions86.5%—
ProofBench26%—
FrontierMath (Feb 2025 set)36.9%—
FrontierMath Tier 4 (v1)16.7%—

Knowledge Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.8 (#3), Gemma 4 26B A4B IT: 45.7 (#85)

BenchmarkGemini 3.1 Pro PreviewGemma 4 26B A4B IT
GPQA Diamond94.4%73.2%
Vectara Hallucination Rate10.4%5.2%
LMArena Expert14851447
Humanity's Last Exam46.4%—
SimpleQA Verified73.5%—

Multimodal Gemma 4 26B A4B IT leads

Gemini 3.1 Pro Preview: 37.9 (#69), Gemma 4 26B A4B IT: 40.6 (#46)

BenchmarkGemini 3.1 Pro PreviewGemma 4 26B A4B IT
LMArena Vision12961260
Blueprint-Bench 226.5%—
Furniture Assembly26.7%—
LMArena Document1444—

Multilingual Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 57.0 (#12), Gemma 4 26B A4B IT: 53.1 (#71)

BenchmarkGemini 3.1 Pro PreviewGemma 4 26B A4B IT
LMArena Non-English14771421
LMArena Chinese15291495
LMArena French14871460
LMArena Russian14981434
LMArena Spanish14791417
LMArena German1491—
LMArena Japanese1493—
LMArena Korean1455—

Instruction Following Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 77.0 (#32), Gemma 4 26B A4B IT: 74.8 (#82)

BenchmarkGemini 3.1 Pro PreviewGemma 4 26B A4B IT
LMArena Instruction Following14661420

Long Context Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 47.4 (#18), Gemma 4 26B A4B IT: 43.6 (#91)

BenchmarkGemini 3.1 Pro PreviewGemma 4 26B A4B IT
LMArena Longer Query14831428
CL-bench20.8%—
CL-bench Life16.9%—

Writing & Preference Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 66.1 (#37), Gemma 4 26B A4B IT: 58.6 (#115)

BenchmarkGemini 3.1 Pro PreviewGemma 4 26B A4B IT
LMArena Text14811434
LMArena Creative Writing14821402
EQ-Bench Creative Writing14911305
LMArena Multi-Turn14881441
EQ-Bench 41142—

Frequently asked questions

Is Gemini 3.1 Pro Preview better than Gemma 4 26B A4B IT?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 43.5 on the Noometry Index. Gemma 4 26B A4B IT costs 32× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.

Which is cheaper, Gemini 3.1 Pro Preview or Gemma 4 26B A4B IT?

Gemma 4 26B A4B IT is cheaper. It lists at $0.09 per million input tokens and $0.30 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.

Is Gemini 3.1 Pro Preview or Gemma 4 26B A4B IT better for coding?

Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.5 versus 39.0 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.1 Pro Preview does, with 1.05M tokens against 262K.

How many benchmarks do Gemini 3.1 Pro Preview and Gemma 4 26B A4B IT share?

28 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and Gemma 4 26B A4B IT has 28.

Related comparisons

Go deeper