Noometry

Model comparison

Gemini 2.5 Flash-Lite vs GPT-4 Turbo

Gemini 2.5 Flash-Lite is the stronger model overall, scoring 36.4 to 30.3 on the Noometry Index.

Last verified . 22 shared benchmarks.

Gemini 2.5 Flash-Lite Google

36.4

Rank #208 Confirmed

GPT-4 Turbo OpenAI

30.3

Rank #281 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Gemini 2.5 Flash-Lite scores higher in 7 categories and GPT-4 Turbo in 2 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Gemini 2.5 Flash-Lite leads 35.5 to 8.6.
  • The biggest single-benchmark swing is WeirdML: 35.2% for Gemini 2.5 Flash-Lite and 18% for GPT-4 Turbo.
  • Gemini 2.5 Flash-Lite is cheaper at $0.10 / $0.40 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
  • Gemini 2.5 Flash-Lite accepts more context: 1.05M tokens versus 128K.

Side by side

Gemini 2.5 Flash-LiteGPT-4 Turbo
ProviderGoogleOpenAI
Noometry Index36.430.3
Released2025-06-172023-11-06
WeightsProprietaryProprietary
Context window1.05M128K
Max output66K4K
Input $ / M tokens$0.10$10
Output $ / M tokens$0.40$30
Results tracked3336

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

Category by category

Coding Gemini 2.5 Flash-Lite leads

Gemini 2.5 Flash-Lite: 38.0 (#167), GPT-4 Turbo: 33.4 (#247)

BenchmarkGemini 2.5 Flash-LiteGPT-4 Turbo
WeirdML35.2%18%
LMArena Coding13731268
BigCodeBench Instruct—48.2%
BigCodeBench Complete—58.2%
ALE-Bench325.9—
HumanEval+—86.6%
MBPP+—73.3%

Agentic & Tool Use Not comparable

Gemini 2.5 Flash-Lite: 27.8 (#89), GPT-4 Turbo: —

BenchmarkGemini 2.5 Flash-LiteGPT-4 Turbo
Berkeley Function Calling Leaderboard36.9%—
METR Time Horizons—36.7%

Reasoning Gemini 2.5 Flash-Lite leads

Gemini 2.5 Flash-Lite: 21.5 (#196), GPT-4 Turbo: 14.9 (#311)

BenchmarkGemini 2.5 Flash-LiteGPT-4 Turbo
LMArena Hard Prompts13771251
DTBench62.8%61.6%
LMCA18.1%9.8%
Epoch Capabilities Index133.93127.25
SimpleBench—25.1%
Kagi LLM Benchmark40.5%—
Chess Puzzles—6%
ForecastBench—59.4

Math Gemini 2.5 Flash-Lite leads

Gemini 2.5 Flash-Lite: 35.5 (#144), GPT-4 Turbo: 8.6 (#316)

BenchmarkGemini 2.5 Flash-LiteGPT-4 Turbo
LMArena Math13731272
FrontierMath (Tiers 1-3)—0.7%
OTIS Mock AIME 2024-2025—6.7%
Omni-MATH48%—
MATH Level 5—46.7%

Knowledge Gemini 2.5 Flash-Lite leads

Gemini 2.5 Flash-Lite: 32.1 (#206), GPT-4 Turbo: 24.3 (#263)

BenchmarkGemini 2.5 Flash-LiteGPT-4 Turbo
LMArena Expert13731223
GPQA Diamond—46.6%
MMLU-Pro53.7%—
Confabulations—28.4%
Vectara Hallucination Rate3.3%—
GPQA (HELM)30.9%—
MMLU—81.3%

Multimodal GPT-4 Turbo leads

Gemini 2.5 Flash-Lite: 28.6 (#109), GPT-4 Turbo: 30.0 (#104)

BenchmarkGemini 2.5 Flash-LiteGPT-4 Turbo
LMArena Vision11981090
VPCT30%—

Multilingual Gemini 2.5 Flash-Lite leads

Gemini 2.5 Flash-Lite: 49.5 (#129), GPT-4 Turbo: 40.7 (#211)

BenchmarkGemini 2.5 Flash-LiteGPT-4 Turbo
LMArena Non-English13691245
LMArena Chinese14041242
LMArena French13881275
LMArena German13901259
LMArena Japanese13591194
LMArena Korean13581187
LMArena Russian13731259
LMArena Spanish13961260

Instruction Following Gemini 2.5 Flash-Lite leads

Gemini 2.5 Flash-Lite: 70.2 (#163), GPT-4 Turbo: 66.0 (#211)

BenchmarkGemini 2.5 Flash-LiteGPT-4 Turbo
LMArena Instruction Following13661250
IFEval81%—

Long Context GPT-4 Turbo leads

Gemini 2.5 Flash-Lite: 33.3 (#257), GPT-4 Turbo: 38.0 (#200)

BenchmarkGemini 2.5 Flash-LiteGPT-4 Turbo
LMArena Longer Query13731254
Fiction.LiveBench47.2%—

Writing & Preference Gemini 2.5 Flash-Lite leads

Gemini 2.5 Flash-Lite: 57.0 (#130), GPT-4 Turbo: 47.9 (#201)

BenchmarkGemini 2.5 Flash-LiteGPT-4 Turbo
LMArena Text13791272
LMArena Creative Writing13661269
LMArena Multi-Turn13671267
WildBench81.8%—

Frequently asked questions

Is Gemini 2.5 Flash-Lite better than GPT-4 Turbo?

Gemini 2.5 Flash-Lite is the stronger model overall, scoring 36.4 to 30.3 on the Noometry Index.

Which is cheaper, Gemini 2.5 Flash-Lite or GPT-4 Turbo?

Gemini 2.5 Flash-Lite is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; GPT-4 Turbo lists at $10 and $30.

Is Gemini 2.5 Flash-Lite or GPT-4 Turbo better for coding?

Gemini 2.5 Flash-Lite scores higher on coding benchmarks: 38.0 versus 33.4 in the Noometry coding category.

Which has the bigger context window?

Gemini 2.5 Flash-Lite does, with 1.05M tokens against 128K.

How many benchmarks do Gemini 2.5 Flash-Lite and GPT-4 Turbo share?

22 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and GPT-4 Turbo has 36.

Related comparisons

Go deeper