Noometry

Model comparison

Gemini 2.5 Pro vs GPT-4o mini

Gemini 2.5 Pro is the stronger model overall, scoring 44.9 to 25.4 on the Noometry Index. GPT-4o mini costs 13× less per token, which makes it the better buy when Gemini 2.5 Pro's lead doesn't matter for your workload.

Last verified . 49 shared benchmarks.

Gemini 2.5 Pro Google

44.9

Rank #67 Confirmed

GPT-4o mini OpenAI

25.4

Rank #337 Confirmed

Summary

  • They share 49 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 10 categories and GPT-4o mini in 0 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Gemini 2.5 Pro leads 55.8 to 17.7.
  • The biggest single-benchmark swing is Aider Polyglot: 83.1% for Gemini 2.5 Pro and 3.6% for GPT-4o mini.
  • GPT-4o mini is cheaper at $0.15 / $0.60 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 128K.

Side by side

Gemini 2.5 ProGPT-4o mini
ProviderGoogleOpenAI
Noometry Index44.925.4
Released2025-03-252024-07-18
WeightsProprietaryProprietary
Context window1.05M128K
Max output66K16K
Input $ / M tokens$1.25$0.15
Output $ / M tokens$10$0.60
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: 42.8 (#86), GPT-4o mini: 21.6 (#330)

BenchmarkGemini 2.5 ProGPT-4o mini
Aider Polyglot83.1%3.6%
WeirdML54%11.8%
LiveBench Coding85.9%43.1%
LMArena Coding14521290
SWE-bench Verified57.6%—
SWE-bench Verified (bash only)53.6%—
LMArena WebDev1227—
SciCode42.8%—
GSO3.9%—
BigCodeBench Instruct—46.1%
BigCodeBench Complete—57.4%
CadEval64%—
ALE-Bench785.52—
AlgoTune1.51—
HumanEval+—83.5%
MBPP+—72.2%

Agentic & Tool Use Gemini 2.5 Pro leads

Gemini 2.5 Pro: 29.1 (#81), GPT-4o mini: 27.2 (#95)

BenchmarkGemini 2.5 ProGPT-4o mini
BALROG43.3%17.4%
Terminal-Bench32.6%—
GDPval23.3%—
Remote Labor Index0.8%—
TheAgentCompany30.3%—
τ²-bench Banking13.7%—
DeepResearch Bench42.8%—
LMArena Search1142—
METR Time Horizons55.4%—
Vending-Bench 2573.64—

Reasoning Gemini 2.5 Pro leads

Gemini 2.5 Pro: 28.8 (#85), GPT-4o mini: 8.7 (#343)

BenchmarkGemini 2.5 ProGPT-4o mini
ARC-AGI-24.9%0%
SimpleBench62.4%10.7%
Kagi LLM Benchmark70.3%28.8%
Chess Puzzles20%0%
LiveBench Reasoning89.8%32.8%
LMArena Hard Prompts14551267
DTBench82.4%54.4%
LiveBench Data Analysis79.9%50%
LMCA34.8%10.4%
Epoch Capabilities Index145.32126.56
LiveBench82.3%41.3%
ARC-AGI-141%—
CritPt2%—
EnigmaEval5.6%—
Mystery Game Puzzles—12%
ForecastBench61.3—
PIQA—88.7%

Math Gemini 2.5 Pro leads

Gemini 2.5 Pro: 31.9 (#191), GPT-4o mini: 9.9 (#307)

BenchmarkGemini 2.5 ProGPT-4o mini
FrontierMath (Tiers 1-3)24.6%0.7%
OTIS Mock AIME 2024-202584.7%6.9%
Omni-MATH41.6%28%
LiveBench Math90.2%36.3%
LMArena Math14501267
MATH Level 595.9%52.6%
FrontierMath Tier 40%—
FrontierMath (Feb 2025 set)14.1%—
FrontierMath Tier 4 (v1)4.2%—
GSM8K—91.3%

Knowledge Gemini 2.5 Pro leads

Gemini 2.5 Pro: 55.8 (#41), GPT-4o mini: 17.7 (#279)

BenchmarkGemini 2.5 ProGPT-4o mini
GPQA Diamond85.3%37.7%
MMLU-Pro86.3%60.3%
Confabulations10.6%37.2%
GPQA (HELM)74.9%36.8%
LMArena Expert14521235
Humanity's Last Exam21.6%—
SimpleQA Verified—8.3%
Vectara Hallucination Rate7%—
BoolQ—88.7%
MMLU—81.8%

Multimodal Gemini 2.5 Pro leads

Gemini 2.5 Pro: 44.5 (#16), GPT-4o mini: 25.3 (#117)

BenchmarkGemini 2.5 ProGPT-4o mini
LMArena Vision12631066
GeoBench86%64%
VPCT48%34%
Video-MME—64.8%
LMArena Document1421—
SpatialViz-Bench44.7%—

Multilingual Gemini 2.5 Pro leads

Gemini 2.5 Pro: 55.5 (#30), GPT-4o mini: 42.2 (#194)

BenchmarkGemini 2.5 ProGPT-4o mini
LMArena Non-English14521266
LMArena Chinese15071264
LMArena French14731296
LMArena German14871272
LMArena Japanese14621216
LMArena Korean14351195
LMArena Russian14601275
LMArena Spanish14731276

Instruction Following Gemini 2.5 Pro leads

Gemini 2.5 Pro: 75.2 (#71), GPT-4o mini: 62.1 (#234)

BenchmarkGemini 2.5 ProGPT-4o mini
LiveBench Instruction Following80.6%56.8%
IFEval84%78.2%
LMArena Instruction Following14361259

Long Context Gemini 2.5 Pro leads

Gemini 2.5 Pro: 59.7 (#5), GPT-4o mini: 39.1 (#181)

BenchmarkGemini 2.5 ProGPT-4o mini
LMArena Longer Query14491289
Fiction.LiveBench91.7%—

Writing & Preference Gemini 2.5 Pro leads

Gemini 2.5 Pro: 63.9 (#60), GPT-4o mini: 39.7 (#243)

BenchmarkGemini 2.5 ProGPT-4o mini
LMArena Text14581286
LMArena Creative Writing14531268
Short-Story Creative Writing83.8%67.2%
EQ-Bench Creative Writing1421873
WildBench85.7%79.1%
LMArena Multi-Turn14531285
LiveBench Language67.8%28.6%

Frequently asked questions

Is Gemini 2.5 Pro better than GPT-4o mini?

Gemini 2.5 Pro is the stronger model overall, scoring 44.9 to 25.4 on the Noometry Index. GPT-4o mini costs 13× 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-4o mini?

GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Gemini 2.5 Pro lists at $1.25 and $10.

Is Gemini 2.5 Pro or GPT-4o mini better for coding?

Gemini 2.5 Pro scores higher on coding benchmarks: 42.8 versus 21.6 in the Noometry coding category.

Which has the bigger context window?

Gemini 2.5 Pro does, with 1.05M tokens against 128K.

How many benchmarks do Gemini 2.5 Pro and GPT-4o mini share?

49 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and GPT-4o mini has 60.

Related comparisons

Go deeper