Noometry

Model comparison

Gemini 3.1 Flash Lite vs GPT-4o mini

Gemini 3.1 Flash Lite is the stronger model overall, scoring 40.8 to 25.5 on the Noometry Index. GPT-4o mini costs 2.1× less per token, which makes it the better buy when Gemini 3.1 Flash Lite's lead doesn't matter for your workload.

Last verified . 27 shared benchmarks.

Gemini 3.1 Flash Lite Google

40.8

Rank #144 Confirmed

GPT-4o mini OpenAI

25.5

Rank #343 Confirmed

Summary

  • They share 27 benchmarks with published results for both. Gemini 3.1 Flash Lite scores higher in 10 categories and GPT-4o mini in 0 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in math, where Gemini 3.1 Flash Lite leads 40.7 to 10.4.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 80% for Gemini 3.1 Flash Lite and 6.9% for GPT-4o mini.
  • GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.25 / $1.50 for Gemini 3.1 Flash Lite.
  • Gemini 3.1 Flash Lite accepts more context: 1.05M tokens versus 128K.

Side by side

Gemini 3.1 Flash LiteGPT-4o mini
ProviderGoogleOpenAI
Noometry Index40.825.5
Released2026-03-032024-07-18
WeightsProprietaryProprietary
Context window1.05M128K
Max output66K16K
Input $ / M tokens$0.25$0.15
Output $ / M tokens$1.50$0.60
Results tracked3860

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

Category by category

Coding Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 37.8 (#188), GPT-4o mini: 22.0 (#335)

BenchmarkGemini 3.1 Flash LiteGPT-4o mini
WeirdML52.2%11.8%
LMArena Coding14001290
Aider Polyglot—3.6%
LMArena WebDev1256—
SciCode41.9%—
BigCodeBench Instruct—46.1%
LiveBench Coding—43.1%
BigCodeBench Complete—57.4%
ALE-Bench797.73—
HumanEval+—83.5%
MBPP+—72.2%

Agentic & Tool Use Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 30.2 (#79), GPT-4o mini: 27.5 (#101)

BenchmarkGemini 3.1 Flash LiteGPT-4o mini
DeepResearch Bench37.3%—
BALROG—17.4%

Reasoning Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 22.9 (#186), GPT-4o mini: 8.7 (#347)

BenchmarkGemini 3.1 Flash LiteGPT-4o mini
Kagi LLM Benchmark67.2%28.8%
Chess Puzzles25%0%
LMArena Hard Prompts14071267
DTBench76.8%54.4%
LMCA35%10.4%
Epoch Capabilities Index144.47126.56
ARC-AGI-2—0%
SimpleBench—10.7%
NYT Connections (extended)8.2%—
CritPt1.1%—
EnigmaEval3%—
Thematic Generalization63.3%—
LiveBench Reasoning—32.8%
Mystery Game Puzzles—12%
LiveBench Data Analysis—50%
ForecastBench54.4—
LiveBench—41.3%
PIQA—88.7%

Math Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 40.7 (#90), GPT-4o mini: 10.4 (#314)

BenchmarkGemini 3.1 Flash LiteGPT-4o mini
FrontierMath (Tiers 1-3)27.7%0.7%
OTIS Mock AIME 2024-202580%6.9%
LMArena Math14281267
Omni-MATH—28%
LiveBench Math—36.3%
MATH Level 5—52.6%
GSM8K—91.3%

Knowledge Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 41.9 (#104), GPT-4o mini: 17.7 (#284)

BenchmarkGemini 3.1 Flash LiteGPT-4o mini
GPQA Diamond81.8%37.7%
LMArena Expert13981235
Humanity's Last Exam8.6%—
SimpleQA Verified—8.3%
MMLU-Pro—60.3%
Confabulations—37.2%
Vectara Hallucination Rate8.2%—
GPQA (HELM)—36.8%
BoolQ—88.7%
MMLU—81.8%

Multimodal Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 39.4 (#60), GPT-4o mini: 25.9 (#122)

BenchmarkGemini 3.1 Flash LiteGPT-4o mini
LMArena Vision12401066
Video-MME—64.8%
GeoBench—64%
VPCT—34%

Multilingual Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 52.3 (#86), GPT-4o mini: 42.0 (#199)

BenchmarkGemini 3.1 Flash LiteGPT-4o mini
LMArena Non-English14111266
LMArena Chinese14611265
LMArena French14241297
LMArena German14291272
LMArena Japanese14131216
LMArena Korean13921195
LMArena Russian14201275
LMArena Spanish14211276

Instruction Following Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 72.7 (#131), GPT-4o mini: 61.9 (#239)

BenchmarkGemini 3.1 Flash LiteGPT-4o mini
LMArena Instruction Following13771258
LiveBench Instruction Following—56.8%
IFEval—78.2%

Long Context Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 42.5 (#122), GPT-4o mini: 39.1 (#186)

BenchmarkGemini 3.1 Flash LiteGPT-4o mini
LMArena Longer Query13941289

Writing & Preference Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 60.9 (#94), GPT-4o mini: 39.5 (#248)

BenchmarkGemini 3.1 Flash LiteGPT-4o mini
LMArena Text14161286
LMArena Creative Writing14011268
LMArena Multi-Turn14171285
Short-Story Creative Writing—67.2%
EQ-Bench Creative Writing—873
WildBench—79.1%
LiveBench Language—28.6%

Frequently asked questions

Is Gemini 3.1 Flash Lite better than GPT-4o mini?

Gemini 3.1 Flash Lite is the stronger model overall, scoring 40.8 to 25.5 on the Noometry Index. GPT-4o mini costs 2.1× less per token, which makes it the better buy when Gemini 3.1 Flash Lite's lead doesn't matter for your workload.

Which is cheaper, Gemini 3.1 Flash Lite 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 3.1 Flash Lite lists at $0.25 and $1.50.

Is Gemini 3.1 Flash Lite or GPT-4o mini better for coding?

Gemini 3.1 Flash Lite scores higher on coding benchmarks: 37.8 versus 22.0 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.1 Flash Lite does, with 1.05M tokens against 128K.

How many benchmarks do Gemini 3.1 Flash Lite and GPT-4o mini share?

27 benchmarks have published results for both models. Gemini 3.1 Flash Lite has 38 scored results on Noometry and GPT-4o mini has 60.

Related comparisons

Go deeper