Noometry

Model comparison

Gemini 2.5 Flash-Lite vs GPT-4

Gemini 2.5 Flash-Lite is the stronger model overall, scoring 37.0 to 29.1 on the Noometry Index.

Last verified . 21 shared benchmarks.

Gemini 2.5 Flash-Lite Google

37.0

Rank #211 Confirmed

GPT-4 OpenAI

29.1

Rank #316 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Gemini 2.5 Flash-Lite scores higher in 7 categories and GPT-4 in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Gemini 2.5 Flash-Lite leads 38.0 to 10.8.
  • The biggest single-benchmark swing is WeirdML: 35.2% for Gemini 2.5 Flash-Lite and 12.4% for GPT-4.
  • Gemini 2.5 Flash-Lite is cheaper at $0.10 / $0.40 per million input/output tokens, against $30 / $60 for GPT-4.
  • Gemini 2.5 Flash-Lite accepts more context: 1.05M tokens versus 8K.

Side by side

Gemini 2.5 Flash-LiteGPT-4
ProviderGoogleOpenAI
Noometry Index37.029.1
Released2025-06-172023-03-14
WeightsProprietaryProprietary
Context window1.05M8K
Max output66K8K
Input $ / M tokens$0.10$30
Output $ / M tokens$0.40$60
Results tracked3338

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: 38.5 (#173), GPT-4: 31.6 (#283)

BenchmarkGemini 2.5 Flash-LiteGPT-4
WeirdML35.2%12.4%
LMArena Coding13731254
BigCodeBench Instruct—46%
BigCodeBench Complete—57.2%
ALE-Bench325.9—
HumanEval+—79.3%

Agentic & Tool Use Not comparable

Gemini 2.5 Flash-Lite: 28.0 (#96), GPT-4: —

BenchmarkGemini 2.5 Flash-LiteGPT-4
Berkeley Function Calling Leaderboard36.9%—
METR Time Horizons—36.1%

Reasoning Gemini 2.5 Flash-Lite leads

Gemini 2.5 Flash-Lite: 22.2 (#205), GPT-4: 17.8 (#289)

BenchmarkGemini 2.5 Flash-LiteGPT-4
LMArena Hard Prompts13771241
DTBench62.8%62.7%
LMCA18.1%17.1%
Epoch Capabilities Index133.94125.89
Kagi LLM Benchmark40.5%—
Chess Puzzles—4%
Mystery Game Puzzles—12%
BIG-Bench Hard—75.1%
ForecastBench—57.8
HellaSwag—95.3%
WinoGrande—87.5%

Math Gemini 2.5 Flash-Lite leads

Gemini 2.5 Flash-Lite: 38.0 (#144), GPT-4: 10.8 (#309)

BenchmarkGemini 2.5 Flash-LiteGPT-4
LMArena Math13731269
OTIS Mock AIME 2024-2025—1.1%
Omni-MATH48%—
MATH Level 5—23%
GSM8K—92%

Knowledge Gemini 2.5 Flash-Lite leads

Gemini 2.5 Flash-Lite: 32.5 (#210), GPT-4: 18.4 (#282)

BenchmarkGemini 2.5 Flash-LiteGPT-4
LMArena Expert13731211
GPQA Diamond—35.7%
MMLU-Pro53.7%—
Vectara Hallucination Rate3.3%—
GPQA (HELM)30.9%—
MMLU—86.4%
TriviaQA—84.8%

Multimodal Not comparable

Gemini 2.5 Flash-Lite: 29.1 (#114), GPT-4: —

BenchmarkGemini 2.5 Flash-LiteGPT-4
LMArena Vision1198—
VPCT30%—

Multilingual Gemini 2.5 Flash-Lite leads

Gemini 2.5 Flash-Lite: 49.3 (#134), GPT-4: 40.6 (#215)

BenchmarkGemini 2.5 Flash-LiteGPT-4
LMArena Non-English13691246
LMArena Chinese14041242
LMArena French13881283
LMArena German13891251
LMArena Japanese13591209
LMArena Korean13601184
LMArena Russian13731251
LMArena Spanish13961261

Instruction Following Gemini 2.5 Flash-Lite leads

Gemini 2.5 Flash-Lite: 70.0 (#168), GPT-4: 65.3 (#222)

BenchmarkGemini 2.5 Flash-LiteGPT-4
LMArena Instruction Following13671241
IFEval81%—

Long Context GPT-4 leads

Gemini 2.5 Flash-Lite: 33.3 (#262), GPT-4: 37.7 (#212)

BenchmarkGemini 2.5 Flash-LiteGPT-4
LMArena Longer Query13731244
Fiction.LiveBench47.2%—

Writing & Preference Gemini 2.5 Flash-Lite leads

Gemini 2.5 Flash-Lite: 56.8 (#135), GPT-4: 34.9 (#268)

BenchmarkGemini 2.5 Flash-LiteGPT-4
LMArena Text13791263
LMArena Creative Writing13671244
LMArena Multi-Turn13661257
EQ-Bench Creative Writing—752
WildBench81.8%—

Frequently asked questions

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

Gemini 2.5 Flash-Lite is the stronger model overall, scoring 37.0 to 29.1 on the Noometry Index.

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

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 lists at $30 and $60.

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

Gemini 2.5 Flash-Lite scores higher on coding benchmarks: 38.5 versus 31.6 in the Noometry coding category.

Which has the bigger context window?

Gemini 2.5 Flash-Lite does, with 1.05M tokens against 8K.

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

21 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and GPT-4 has 38.

Related comparisons

Go deeper