Noometry

Model comparison

Gemini 3.1 Pro Preview vs o1

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 40.9 on the Noometry Index.

Last verified . 33 shared benchmarks.

Gemini 3.1 Pro Preview Google

56.7

Rank #23 Confirmed

o1 OpenAI

40.9

Rank #143 Confirmed

Summary

  • They share 33 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 8 categories and o1 in 2 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 27.9.
  • The biggest single-benchmark swing is ARC-AGI-1: 98% for Gemini 3.1 Pro Preview and 30.7% for o1.
  • Gemini 3.1 Pro Preview is cheaper at $2 / $12 per million input/output tokens, against $15 / $60 for o1.
  • Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 200K.

Side by side

Gemini 3.1 Pro Previewo1
ProviderGoogleOpenAI
Noometry Index56.740.9
Released2026-02-192024-09-12
WeightsProprietaryProprietary
Context window1.05M200K
Max output66K100K
Input $ / M tokens$2$15
Output $ / M tokens$12$60
Results tracked7152

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

Category by category

Coding o1 leads

Gemini 3.1 Pro Preview: 42.5 (#99), o1: 46.1 (#70)

BenchmarkGemini 3.1 Pro Previewo1
WeirdML72.1%47.6%
LMArena Coding14841367
SWE-bench Verified75.6%—
DeepSWE11.7%—
Aider Polyglot—61.7%
LMArena WebDev1447—
SciCode58.9%—
GSO22.6%—
LiveBench Coding—69.7%
MirrorCode8.9%—
CadEval—56%
ALE-Bench1,161—
AlgoTune2.02—
HumanEval+—89%
MBPP+—80.2%

Agentic & Tool Use Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 37.7 (#34), o1: 24.6 (#117)

BenchmarkGemini 3.1 Pro Previewo1
METR Time Horizons77%51.1%
Terminal-Bench80.2%—
APEX-Agents35.3%—
τ²-bench Banking26%—
Cybench—10%
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), o1: 27.9 (#111)

BenchmarkGemini 3.1 Pro Previewo1
SimpleBench79.6%41.7%
ARC-AGI-198%30.7%
Chess Puzzles55%15%
EnigmaEval36.8%5.7%
LMArena Hard Prompts14851371
DTBench97.1%74.7%
LMCA53.8%22.3%
Epoch Capabilities Index154.77141.91
ARC-AGI-277.1%—
NYT Connections (extended)97.4%—
CritPt17.7%—
Thematic Generalization79.4%—
EBR-Bench14.3%—
LiveBench Reasoning—91.6%
Mystery Game Puzzles34%—
LiveBench Data Analysis—65.5%
ForecastBench59—
LiveBench—75.7%

Math Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 62.1 (#34), o1: 36.1 (#175)

BenchmarkGemini 3.1 Pro Previewo1
FrontierMath (Tiers 1-3)59.6%14.7%
OTIS Mock AIME 2024-202595.6%73.3%
LMArena Math14851388
FrontierMath (Feb 2025 set)36.9%9.3%
FrontierMath Tier 426.8%—
MathArena Final-Answer Competitions86.5%—
ProofBench26%—
LiveBench Math—80.3%
MATH Level 5—94.7%
FrontierMath Tier 4 (v1)16.7%—

Knowledge Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.8 (#3), o1: 41.5 (#110)

BenchmarkGemini 3.1 Pro Previewo1
GPQA Diamond94.4%76.8%
Humanity's Last Exam46.4%8%
SimpleQA Verified73.5%41.1%
LMArena Expert14851361
Confabulations—11.7%
Vectara Hallucination Rate10.4%—

Multimodal Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 37.9 (#69), o1: 34.2 (#93)

BenchmarkGemini 3.1 Pro Previewo1
LMArena Vision12961168
GeoBench—80%
VPCT—37%
Blueprint-Bench 226.5%—
Furniture Assembly26.7%—
LMArena Document1444—
SpatialViz-Bench—41.4%

Multilingual Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 57.0 (#12), o1: 48.6 (#142)

BenchmarkGemini 3.1 Pro Previewo1
LMArena Non-English14771358
LMArena Chinese15291394
LMArena French14871344
LMArena German14911337
LMArena Japanese14931346
LMArena Korean14551396
LMArena Russian14981356
LMArena Spanish14791345

Instruction Following Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 77.0 (#32), o1: 74.8 (#86)

BenchmarkGemini 3.1 Pro Previewo1
LMArena Instruction Following14661367
LiveBench Instruction Following—81.5%

Long Context o1 leads

Gemini 3.1 Pro Preview: 47.4 (#18), o1: 50.3 (#9)

BenchmarkGemini 3.1 Pro Previewo1
LMArena Longer Query14831378
Fiction.LiveBench—83.3%
CL-bench20.8%—
CL-bench Life16.9%—

Writing & Preference Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 66.1 (#37), o1: 55.6 (#144)

BenchmarkGemini 3.1 Pro Previewo1
LMArena Text14811366
LMArena Creative Writing14821348
LMArena Multi-Turn14881369
Short-Story Creative Writing—70.2%
EQ-Bench Creative Writing1491—
EQ-Bench 41142—
LiveBench Language—65.4%

Frequently asked questions

Is Gemini 3.1 Pro Preview better than o1?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 40.9 on the Noometry Index.

Which is cheaper, Gemini 3.1 Pro Preview or o1?

Gemini 3.1 Pro Preview is cheaper. It lists at $2 per million input tokens and $12 per million output tokens; o1 lists at $15 and $60.

Is Gemini 3.1 Pro Preview or o1 better for coding?

o1 scores higher on coding benchmarks: 46.1 versus 42.5 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 o1 share?

33 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and o1 has 52.

Related comparisons

Go deeper