Noometry

Model comparison

Gemini 2.5 Pro vs GPT-5 Mini

Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 41.8 on the Noometry Index. GPT-5 Mini costs 5.0× less per token, which makes it the better buy when Gemini 2.5 Pro's lead doesn't matter for your workload.

Last verified . 55 shared benchmarks.

Gemini 2.5 Pro Google

45.0

Rank #75 Confirmed

GPT-5 Mini OpenAI

41.8

Rank #128 Confirmed

Summary

  • They share 55 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 7 categories and GPT-5 Mini in 3 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Gemini 2.5 Pro leads 59.8 to 41.9.
  • The biggest single-benchmark swing is Omni-MATH: 41.6% for Gemini 2.5 Pro and 72.2% for GPT-5 Mini.
  • GPT-5 Mini is cheaper at $0.25 / $2 per million input/output tokens, against $1.25 / $10 for Gemini 2.5 Pro.
  • Gemini 2.5 Pro accepts more context: 1.05M tokens versus 400K.

Side by side

Gemini 2.5 ProGPT-5 Mini
ProviderGoogleOpenAI
Noometry Index45.041.8
Released2025-03-252025-08-07
WeightsProprietaryProprietary
Context window1.05M400K
Max output66K128K
Input $ / M tokens$1.25$0.25
Output $ / M tokens$10$2
Results tracked7860

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

Category by category

Coding Gemini 2.5 Pro leads

Gemini 2.5 Pro: 42.4 (#101), GPT-5 Mini: 40.1 (#146)

BenchmarkGemini 2.5 ProGPT-5 Mini
SWE-bench Verified57.6%64.7%
SWE-bench Verified (bash only)53.6%59.8%
SciCode42.8%39.2%
WeirdML54%52.7%
LMArena Coding14521406
ALE-Bench785.52799.77
AlgoTune1.511.38
Aider Polyglot83.1%—
LMArena WebDev1227—
SWE-bench Multilingual—39.7%
GSO3.9%—
LiveBench Coding85.9%—
CadEval64%—

Agentic & Tool Use GPT-5 Mini leads

Gemini 2.5 Pro: 29.2 (#88), GPT-5 Mini: 31.1 (#70)

BenchmarkGemini 2.5 ProGPT-5 Mini
Terminal-Bench32.6%34.8%
Vending-Bench 2573.64-31.18
Berkeley Function Calling Leaderboard—55.5%
GDPval23.3%—
Remote Labor Index0.8%—
TheAgentCompany30.3%—
τ²-bench Banking13.7%—
DeepResearch Bench42.8%—
BALROG43.3%—
LMArena Search1142—
METR Time Horizons55.4%—

Reasoning Gemini 2.5 Pro leads

Gemini 2.5 Pro: 28.8 (#99), GPT-5 Mini: 23.9 (#168)

BenchmarkGemini 2.5 ProGPT-5 Mini
ARC-AGI-24.9%4.4%
Kagi LLM Benchmark70.3%70.3%
ARC-AGI-141%54.3%
CritPt2%0%
Chess Puzzles20%30%
EnigmaEval5.6%8.2%
LMArena Hard Prompts14551380
DTBench82.4%80.5%
LMCA34.8%34.2%
Epoch Capabilities Index145.32145.52
ForecastBench61.361
SimpleBench62.4%—
LiveBench Reasoning89.8%—
Mystery Game Puzzles—10%
LiveBench Data Analysis79.9%—
LiveBench82.3%—

Math GPT-5 Mini leads

Gemini 2.5 Pro: 32.5 (#213), GPT-5 Mini: 46.7 (#69)

BenchmarkGemini 2.5 ProGPT-5 Mini
FrontierMath (Tiers 1-3)24.6%46.7%
FrontierMath Tier 40%12.2%
OTIS Mock AIME 2024-202584.7%86.7%
Omni-MATH41.6%72.2%
LMArena Math14501378
MATH Level 595.9%97.8%
FrontierMath (Feb 2025 set)14.1%27.2%
FrontierMath Tier 4 (v1)4.2%6.3%
ProofBench—9%
LiveBench Math90.2%—

Knowledge Gemini 2.5 Pro leads

Gemini 2.5 Pro: 56.0 (#46), GPT-5 Mini: 45.6 (#86)

BenchmarkGemini 2.5 ProGPT-5 Mini
GPQA Diamond85.3%75%
Humanity's Last Exam21.6%19.4%
MMLU-Pro86.3%83.5%
Confabulations10.6%13.3%
Vectara Hallucination Rate7%12.9%
GPQA (HELM)74.9%75.6%
LMArena Expert14521379
SimpleQA Verified—21.6%

Multimodal Gemini 2.5 Pro leads

Gemini 2.5 Pro: 45.2 (#18), GPT-5 Mini: 35.6 (#85)

BenchmarkGemini 2.5 ProGPT-5 Mini
LMArena Vision12631202
VPCT48%40.2%
GeoBench86%—
LMArena Document1421—
SpatialViz-Bench44.7%—

Multilingual Gemini 2.5 Pro leads

Gemini 2.5 Pro: 55.3 (#31), GPT-5 Mini: 48.9 (#137)

BenchmarkGemini 2.5 ProGPT-5 Mini
LMArena Non-English14511363
LMArena Chinese15071385
LMArena French14721386
LMArena German14871366
LMArena Japanese14611341
LMArena Korean14341308
LMArena Russian14611362
LMArena Spanish14731355

Instruction Following GPT-5 Mini leads

Gemini 2.5 Pro: 75.0 (#75), GPT-5 Mini: 76.2 (#46)

BenchmarkGemini 2.5 ProGPT-5 Mini
IFEval84%92.7%
LMArena Instruction Following14371357
LiveBench Instruction Following80.6%—

Long Context Gemini 2.5 Pro leads

Gemini 2.5 Pro: 59.8 (#5), GPT-5 Mini: 41.9 (#132)

BenchmarkGemini 2.5 ProGPT-5 Mini
Fiction.LiveBench91.7%69.4%
LMArena Longer Query14491355

Writing & Preference Gemini 2.5 Pro leads

Gemini 2.5 Pro: 63.7 (#62), GPT-5 Mini: 55.2 (#148)

BenchmarkGemini 2.5 ProGPT-5 Mini
LMArena Text14581373
LMArena Creative Writing14541325
Short-Story Creative Writing83.8%83.1%
EQ-Bench Creative Writing14211313
WildBench85.7%85.5%
LMArena Multi-Turn14531363
LiveBench Language67.8%—

Frequently asked questions

Is Gemini 2.5 Pro better than GPT-5 Mini?

Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 41.8 on the Noometry Index. GPT-5 Mini costs 5.0× less per token, which makes it the better buy when Gemini 2.5 Pro's lead doesn't matter for your workload.

Which is cheaper, Gemini 2.5 Pro 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 2.5 Pro lists at $1.25 and $10.

Is Gemini 2.5 Pro or GPT-5 Mini better for coding?

Gemini 2.5 Pro scores higher on coding benchmarks: 42.4 versus 40.1 in the Noometry coding category.

Which has the bigger context window?

Gemini 2.5 Pro does, with 1.05M tokens against 400K.

How many benchmarks do Gemini 2.5 Pro and GPT-5 Mini share?

55 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and GPT-5 Mini has 60.

Related comparisons

Go deeper