Noometry

Model comparison

Gemini 3.1 Pro Preview vs GPT-5 Mini

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 41.8 on the Noometry Index. GPT-5 Mini costs 6.5× 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 . 46 shared benchmarks.

Gemini 3.1 Pro Preview Google

56.7

Rank #23 Confirmed

GPT-5 Mini OpenAI

41.8

Rank #128 Confirmed

Summary

  • They share 46 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 10 categories and GPT-5 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 23.9.
  • The biggest single-benchmark swing is ARC-AGI-2: 77.1% for Gemini 3.1 Pro Preview and 4.4% for GPT-5 Mini.
  • GPT-5 Mini is cheaper at $0.25 / $2 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 400K.

Side by side

Gemini 3.1 Pro PreviewGPT-5 Mini
ProviderGoogleOpenAI
Noometry Index56.741.8
Released2026-02-192025-08-07
WeightsProprietaryProprietary
Context window1.05M400K
Max output66K128K
Input $ / M tokens$2$0.25
Output $ / M tokens$12$2
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), GPT-5 Mini: 40.1 (#146)

BenchmarkGemini 3.1 Pro PreviewGPT-5 Mini
SWE-bench Verified75.6%64.7%
SciCode58.9%39.2%
WeirdML72.1%52.7%
LMArena Coding14841406
ALE-Bench1,161799.77
AlgoTune2.021.38
DeepSWE11.7%—
SWE-bench Verified (bash only)—59.8%
LMArena WebDev1447—
SWE-bench Multilingual—39.7%
GSO22.6%—
MirrorCode8.9%—

Agentic & Tool Use Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 37.7 (#34), GPT-5 Mini: 31.1 (#70)

BenchmarkGemini 3.1 Pro PreviewGPT-5 Mini
Terminal-Bench80.2%34.8%
Vending-Bench 23,774-31.18
APEX-Agents35.3%—
Berkeley Function Calling Leaderboard—55.5%
τ²-bench Banking26%—
DeepResearch Bench47.8%—
PostTrainBench22%—
BALROG57%—
ExploitBench26.1%—
GBAEval0.8%—
GDP.pdf17%—
LMArena Search1211—
METR Time Horizons77%—

Reasoning Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.7 (#12), GPT-5 Mini: 23.9 (#168)

BenchmarkGemini 3.1 Pro PreviewGPT-5 Mini
ARC-AGI-277.1%4.4%
ARC-AGI-198%54.3%
CritPt17.7%0%
Chess Puzzles55%30%
EnigmaEval36.8%8.2%
LMArena Hard Prompts14851380
Mystery Game Puzzles34%10%
DTBench97.1%80.5%
LMCA53.8%34.2%
Epoch Capabilities Index154.77145.52
ForecastBench5961
SimpleBench79.6%—
Kagi LLM Benchmark—70.3%
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), GPT-5 Mini: 46.7 (#69)

BenchmarkGemini 3.1 Pro PreviewGPT-5 Mini
FrontierMath (Tiers 1-3)59.6%46.7%
FrontierMath Tier 426.8%12.2%
OTIS Mock AIME 2024-202595.6%86.7%
ProofBench26%9%
LMArena Math14851378
FrontierMath (Feb 2025 set)36.9%27.2%
FrontierMath Tier 4 (v1)16.7%6.3%
MathArena Final-Answer Competitions86.5%—
Omni-MATH—72.2%
MATH Level 5—97.8%

Knowledge Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 71.8 (#3), GPT-5 Mini: 45.6 (#86)

BenchmarkGemini 3.1 Pro PreviewGPT-5 Mini
GPQA Diamond94.4%75%
Humanity's Last Exam46.4%19.4%
SimpleQA Verified73.5%21.6%
Vectara Hallucination Rate10.4%12.9%
LMArena Expert14851379
MMLU-Pro—83.5%
Confabulations—13.3%
GPQA (HELM)—75.6%

Multimodal Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 37.9 (#69), GPT-5 Mini: 35.6 (#85)

BenchmarkGemini 3.1 Pro PreviewGPT-5 Mini
LMArena Vision12961202
VPCT—40.2%
Blueprint-Bench 226.5%—
Furniture Assembly26.7%—
LMArena Document1444—

Multilingual Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 57.0 (#12), GPT-5 Mini: 48.9 (#137)

BenchmarkGemini 3.1 Pro PreviewGPT-5 Mini
LMArena Non-English14771363
LMArena Chinese15291385
LMArena French14871386
LMArena German14911366
LMArena Japanese14931341
LMArena Korean14551308
LMArena Russian14981362
LMArena Spanish14791355

Instruction Following Too close to call

Gemini 3.1 Pro Preview: 77.0 (#32), GPT-5 Mini: 76.2 (#46)

BenchmarkGemini 3.1 Pro PreviewGPT-5 Mini
LMArena Instruction Following14661357
IFEval—92.7%

Long Context Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 47.4 (#18), GPT-5 Mini: 41.9 (#132)

BenchmarkGemini 3.1 Pro PreviewGPT-5 Mini
LMArena Longer Query14831355
Fiction.LiveBench—69.4%
CL-bench20.8%—
CL-bench Life16.9%—

Writing & Preference Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 66.1 (#37), GPT-5 Mini: 55.2 (#148)

BenchmarkGemini 3.1 Pro PreviewGPT-5 Mini
LMArena Text14811373
LMArena Creative Writing14821325
EQ-Bench Creative Writing14911313
LMArena Multi-Turn14881363
Short-Story Creative Writing—83.1%
WildBench—85.5%
EQ-Bench 41142—

Frequently asked questions

Is Gemini 3.1 Pro Preview better than GPT-5 Mini?

Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 41.8 on the Noometry Index. GPT-5 Mini costs 6.5× 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 GPT-5 Mini?

GPT-5 Mini is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.

Is Gemini 3.1 Pro Preview or GPT-5 Mini better for coding?

Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.5 versus 40.1 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.1 Pro Preview does, with 1.05M tokens against 400K.

How many benchmarks do Gemini 3.1 Pro Preview and GPT-5 Mini share?

46 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and GPT-5 Mini has 60.

Related comparisons

Go deeper