Noometry

Model comparison

Gemini 3.1 Pro Preview vs o4-mini

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 41.6 on the Noometry Index. o4-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 . 43 shared benchmarks.

Gemini 3.1 Pro Preview Google

56.7

Rank #23 Confirmed

o4-mini OpenAI

41.6

Rank #132 Confirmed

Summary

  • They share 43 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 9 categories and o4-mini in 1 category; 10 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 24.6.
  • The biggest single-benchmark swing is ARC-AGI-2: 77.1% for Gemini 3.1 Pro Preview and 6.1% for o4-mini.
  • o4-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 Previewo4-mini
ProviderGoogleOpenAI
Noometry Index56.741.6
Released2026-02-192025-04-16
WeightsProprietaryProprietary
Context window1.05M200K
Max output66K100K
Input $ / M tokens$2$1.10
Output $ / M tokens$12$4.40
Results tracked7160

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), o4-mini: 40.9 (#127)

BenchmarkGemini 3.1 Pro Previewo4-mini
GSO22.6%3.6%
WeirdML72.1%52.6%
LMArena Coding14841368
ALE-Bench1,161826.17
AlgoTune2.021.72
SWE-bench Verified75.6%—
DeepSWE11.7%—
SWE-bench Verified (bash only)—45%
Aider Polyglot—72%
LMArena WebDev1447—
SciCode58.9%—
MirrorCode8.9%—
CadEval—62%

Agentic & Tool Use Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 37.7 (#34), o4-mini: 32.6 (#61)

BenchmarkGemini 3.1 Pro Previewo4-mini
METR Time Horizons77%63.9%
Terminal-Bench80.2%—
APEX-Agents35.3%—
Berkeley Function Calling Leaderboard—53.2%
GDPval—25.3%
τ²-bench Banking26%—
DeepResearch Bench47.8%—
PostTrainBench22%—
BALROG57%—
ExploitBench26.1%—
GBAEval0.8%—
GDP.pdf17%—
LMArena Search1211—
Vending-Bench 23,774—

Reasoning Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.7 (#12), o4-mini: 24.6 (#162)

BenchmarkGemini 3.1 Pro Previewo4-mini
ARC-AGI-277.1%6.1%
SimpleBench79.6%38.7%
ARC-AGI-198%58.7%
CritPt17.7%0.6%
Chess Puzzles55%26%
EnigmaEval36.8%9.2%
LMArena Hard Prompts14851351
Mystery Game Puzzles34%5%
DTBench97.1%77.6%
LMCA53.8%26.5%
Epoch Capabilities Index154.77145.64
ForecastBench5961.8
Kagi LLM Benchmark—67.6%
NYT Connections (extended)97.4%—
Thematic Generalization79.4%—
EBR-Bench14.3%—

Math Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 62.1 (#34), o4-mini: 40.8 (#89)

BenchmarkGemini 3.1 Pro Previewo4-mini
FrontierMath (Tiers 1-3)59.6%36.1%
FrontierMath Tier 426.8%4.9%
OTIS Mock AIME 2024-202595.6%81.7%
LMArena Math14851389
FrontierMath (Feb 2025 set)36.9%24.8%
FrontierMath Tier 4 (v1)16.7%6.3%
MathArena Final-Answer Competitions86.5%—
ProofBench26%—
Omni-MATH—72%
MATH Level 5—97.8%

Knowledge Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.8 (#3), o4-mini: 43.6 (#91)

BenchmarkGemini 3.1 Pro Previewo4-mini
GPQA Diamond94.4%79.6%
Humanity's Last Exam46.4%18.1%
SimpleQA Verified73.5%19.6%
Vectara Hallucination Rate10.4%18.6%
LMArena Expert14851343
MMLU-Pro—82%
Confabulations—15.8%
GPQA (HELM)—73.5%

Multimodal o4-mini leads

Gemini 3.1 Pro Preview: 37.9 (#69), o4-mini: 40.2 (#49)

BenchmarkGemini 3.1 Pro Previewo4-mini
LMArena Vision12961194
GeoBench—64%
VPCT—57.5%
Blueprint-Bench 226.5%—
Furniture Assembly26.7%—
LMArena Document1444—

Multilingual Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 57.0 (#12), o4-mini: 47.0 (#154)

BenchmarkGemini 3.1 Pro Previewo4-mini
LMArena Non-English14771337
LMArena Chinese15291354
LMArena French14871364
LMArena German14911336
LMArena Japanese14931308
LMArena Korean14551312
LMArena Russian14981334
LMArena Spanish14791347

Instruction Following Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 77.0 (#32), o4-mini: 75.2 (#68)

BenchmarkGemini 3.1 Pro Previewo4-mini
LMArena Instruction Following14661321
IFEval—92.8%

Long Context Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 47.4 (#18), o4-mini: 45.5 (#33)

BenchmarkGemini 3.1 Pro Previewo4-mini
LMArena Longer Query14831315
Fiction.LiveBench—77.8%
CL-bench20.8%—
CL-bench Life16.9%—

Writing & Preference Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 66.1 (#37), o4-mini: 54.0 (#152)

BenchmarkGemini 3.1 Pro Previewo4-mini
LMArena Text14811353
LMArena Creative Writing14821294
LMArena Multi-Turn14881350
Short-Story Creative Writing—75%
EQ-Bench Creative Writing1491—
WildBench—85.4%
EQ-Bench 41142—

Frequently asked questions

Is Gemini 3.1 Pro Preview better than o4-mini?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 41.6 on the Noometry Index. o4-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 o4-mini?

o4-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 o4-mini better for coding?

Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.5 versus 40.9 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 o4-mini share?

43 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and o4-mini has 60.

Related comparisons

Go deeper