Noometry

Model comparison

Gemini 3.1 Pro Preview vs Gemma 2 27B

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 29.4 on the Noometry Index. Gemma 2 27B costs 6.9× 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 . 22 shared benchmarks.

Gemini 3.1 Pro Preview Google

56.7

Rank #23 Confirmed

Gemma 2 27B Google

29.4

Rank #312 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 8 categories and Gemma 2 27B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 15.3.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 95.6% for Gemini 3.1 Pro Preview and 1.4% for Gemma 2 27B.
  • Gemma 2 27B is cheaper at $0.65 / $0.65 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 8K.
  • Gemma 2 27B has downloadable open weights; the other is API-only.

Side by side

Gemini 3.1 Pro PreviewGemma 2 27B
ProviderGoogleGoogle
Noometry Index56.729.4
Released2026-02-192024-06-24
WeightsProprietaryOpen
Context window1.05M8K
Max output66K2K
Input $ / M tokens$2$0.65
Output $ / M tokens$12$0.65
Results tracked7134

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 2 27B: 34.1 (#246)

BenchmarkGemini 3.1 Pro PreviewGemma 2 27B
LMArena Coding14841211
SWE-bench Verified75.6%—
DeepSWE11.7%—
LMArena WebDev1447—
SciCode58.9%—
GSO22.6%—
WeirdML72.1%—
BigCodeBench Instruct—42.8%
LiveBench Coding—36%
MirrorCode8.9%—
BigCodeBench Complete—52.5%
ALE-Bench1,161—
AlgoTune2.02—

Agentic & Tool Use Not comparable

Gemini 3.1 Pro Preview: 37.7 (#34), Gemma 2 27B: —

BenchmarkGemini 3.1 Pro PreviewGemma 2 27B
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 2 27B: 15.3 (#315)

BenchmarkGemini 3.1 Pro PreviewGemma 2 27B
LMArena Hard Prompts14851198
DTBench97.1%48%
LMCA53.8%7.1%
Epoch Capabilities Index154.77122.08
ARC-AGI-277.1%—
SimpleBench79.6%—
NYT Connections (extended)97.4%—
ARC-AGI-198%—
CritPt17.7%—
Chess Puzzles55%—
EnigmaEval36.8%—
Thematic Generalization79.4%—
EBR-Bench14.3%—
LiveBench Reasoning—28.1%
Mystery Game Puzzles34%—
LiveBench Data Analysis—47.9%
ForecastBench59—
LiveBench—38.2%

Math Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 62.1 (#34), Gemma 2 27B: 10.7 (#311)

BenchmarkGemini 3.1 Pro PreviewGemma 2 27B
OTIS Mock AIME 2024-202595.6%1.4%
LMArena Math14851212
FrontierMath (Tiers 1-3)59.6%—
FrontierMath Tier 426.8%—
MathArena Final-Answer Competitions86.5%—
ProofBench26%—
LiveBench Math—26.5%
MATH Level 5—27.9%
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 2 27B: 19.0 (#280)

BenchmarkGemini 3.1 Pro PreviewGemma 2 27B
GPQA Diamond94.4%36.5%
LMArena Expert14851172
Humanity's Last Exam46.4%—
SimpleQA Verified73.5%—
Confabulations—27.1%
Vectara Hallucination Rate10.4%—
MMLU—75.7%

Multimodal Not comparable

Gemini 3.1 Pro Preview: 37.9 (#69), Gemma 2 27B: —

BenchmarkGemini 3.1 Pro PreviewGemma 2 27B
LMArena Vision1296—
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 2 27B: 38.6 (#226)

BenchmarkGemini 3.1 Pro PreviewGemma 2 27B
LMArena Non-English14771217
LMArena Chinese15291221
LMArena French14871247
LMArena German14911209
LMArena Japanese14931175
LMArena Korean14551174
LMArena Russian14981234
LMArena Spanish14791228

Instruction Following Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 77.0 (#32), Gemma 2 27B: 60.5 (#249)

BenchmarkGemini 3.1 Pro PreviewGemma 2 27B
LMArena Instruction Following14661206
LiveBench Instruction Following—58.1%

Long Context Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 47.4 (#18), Gemma 2 27B: 37.3 (#218)

BenchmarkGemini 3.1 Pro PreviewGemma 2 27B
LMArena Longer Query14831231
CL-bench20.8%—
CL-bench Life16.9%—

Writing & Preference Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 66.1 (#37), Gemma 2 27B: 44.2 (#225)

BenchmarkGemini 3.1 Pro PreviewGemma 2 27B
LMArena Text14811231
LMArena Creative Writing14821241
LMArena Multi-Turn14881224
EQ-Bench Creative Writing1491—
EQ-Bench 41142—
LiveBench Language—32.6%

Frequently asked questions

Is Gemini 3.1 Pro Preview better than Gemma 2 27B?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 29.4 on the Noometry Index. Gemma 2 27B costs 6.9× 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 2 27B?

Gemma 2 27B is cheaper. It lists at $0.65 per million input tokens and $0.65 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.

Is Gemini 3.1 Pro Preview or Gemma 2 27B better for coding?

Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.5 versus 34.1 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.1 Pro Preview does, with 1.05M tokens against 8K.

How many benchmarks do Gemini 3.1 Pro Preview and Gemma 2 27B share?

22 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and Gemma 2 27B has 34.

Related comparisons

Go deeper