Noometry

Model comparison

Gemini 3.1 Pro Preview vs o3-mini

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 36.7 on the Noometry Index. o3-mini costs 2.3× 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 . 37 shared benchmarks.

Gemini 3.1 Pro Preview Google

56.7

Rank #23 Confirmed

o3-mini OpenAI

36.7

Rank #212 Confirmed

Summary

  • They share 37 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 9 categories and o3-mini in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 16.3.
  • The biggest single-benchmark swing is ARC-AGI-2: 77.1% for Gemini 3.1 Pro Preview and 3% for o3-mini.
  • o3-mini is cheaper at $1.10 / $4.40 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 200K.

Side by side

Gemini 3.1 Pro Previewo3-mini
ProviderGoogleOpenAI
Noometry Index56.736.7
Released2026-02-192024-12-20
WeightsProprietaryProprietary
Context window1.05M200K
Max output66K100K
Input $ / M tokens$2$1.10
Output $ / M tokens$12$4.40
Results tracked7151

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), o3-mini: 40.8 (#132)

BenchmarkGemini 3.1 Pro Previewo3-mini
SciCode58.9%39.8%
GSO22.6%1.3%
WeirdML72.1%43.7%
LMArena Coding14841378
SWE-bench Verified75.6%—
DeepSWE11.7%—
Aider Polyglot—60.4%
LMArena WebDev1447—
LiveBench Coding—82.7%
MirrorCode8.9%—
CadEval—54%
ALE-Bench1,161—
AlgoTune2.02—

Agentic & Tool Use Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 37.7 (#34), o3-mini: 29.6 (#84)

BenchmarkGemini 3.1 Pro Previewo3-mini
Terminal-Bench80.2%—
APEX-Agents35.3%—
τ²-bench Banking26%—
Cybench—22.5%
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), o3-mini: 16.3 (#305)

BenchmarkGemini 3.1 Pro Previewo3-mini
ARC-AGI-277.1%3%
SimpleBench79.6%22.8%
ARC-AGI-198%34.5%
CritPt17.7%0.3%
Chess Puzzles55%17%
LMArena Hard Prompts14851366
Mystery Game Puzzles34%7%
DTBench97.1%68.8%
LMCA53.8%19%
Epoch Capabilities Index154.77140.34
ForecastBench5959.6
NYT Connections (extended)97.4%—
EnigmaEval36.8%—
Thematic Generalization79.4%—
EBR-Bench14.3%—
LiveBench Reasoning—89.6%
LiveBench Data Analysis—70.6%
LiveBench—75.9%

Math Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 62.1 (#34), o3-mini: 28.1 (#244)

BenchmarkGemini 3.1 Pro Previewo3-mini
FrontierMath (Tiers 1-3)59.6%18.6%
FrontierMath Tier 426.8%0%
OTIS Mock AIME 2024-202595.6%76.9%
LMArena Math14851396
FrontierMath (Feb 2025 set)36.9%12.4%
FrontierMath Tier 4 (v1)16.7%4.2%
MathArena Final-Answer Competitions86.5%—
ProofBench26%—
LiveBench Math—77.3%
MATH Level 5—96.5%

Knowledge Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.8 (#3), o3-mini: 38.3 (#146)

BenchmarkGemini 3.1 Pro Previewo3-mini
GPQA Diamond94.4%77%
SimpleQA Verified73.5%15.3%
LMArena Expert14851364
Humanity's Last Exam46.4%—
Confabulations—17.9%
Vectara Hallucination Rate10.4%—

Multimodal Not comparable

Gemini 3.1 Pro Preview: 37.9 (#69), o3-mini: —

BenchmarkGemini 3.1 Pro Previewo3-mini
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), o3-mini: 45.7 (#164)

BenchmarkGemini 3.1 Pro Previewo3-mini
LMArena Non-English14771319
LMArena Chinese15291379
LMArena French14871334
LMArena German14911303
LMArena Japanese14931286
LMArena Korean14551314
LMArena Russian14981304
LMArena Spanish14791321

Instruction Following Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 77.0 (#32), o3-mini: 75.1 (#72)

BenchmarkGemini 3.1 Pro Previewo3-mini
LMArena Instruction Following14661337
LiveBench Instruction Following—84.4%

Long Context Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 47.4 (#18), o3-mini: 33.8 (#256)

BenchmarkGemini 3.1 Pro Previewo3-mini
LMArena Longer Query14831343
Fiction.LiveBench—50%
CL-bench20.8%—
CL-bench Life16.9%—

Writing & Preference Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 66.1 (#37), o3-mini: 50.3 (#182)

BenchmarkGemini 3.1 Pro Previewo3-mini
LMArena Text14811337
LMArena Creative Writing14821286
LMArena Multi-Turn14881320
Short-Story Creative Writing—61.7%
EQ-Bench Creative Writing1491—
EQ-Bench 41142—
LiveBench Language—50.7%

Frequently asked questions

Is Gemini 3.1 Pro Preview better than o3-mini?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 36.7 on the Noometry Index. o3-mini costs 2.3× 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 o3-mini?

o3-mini is cheaper. It lists at $1.10 per million input tokens and $4.40 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.

Is Gemini 3.1 Pro Preview or o3-mini better for coding?

Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.5 versus 40.8 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.1 Pro Preview does, with 1.05M tokens against 200K.

How many benchmarks do Gemini 3.1 Pro Preview and o3-mini share?

37 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and o3-mini has 51.

Related comparisons

Go deeper