Noometry

Model comparison

Gemini 2.5 Flash-Lite vs GPT-5.3 Codex

GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 37.0 on the Noometry Index. Gemini 2.5 Flash-Lite costs 27× less per token, which makes it the better buy when GPT-5.3 Codex's lead doesn't matter for your workload.

Last verified . 3 shared benchmarks.

Gemini 2.5 Flash-Lite Google

37.0

Rank #211 Confirmed

GPT-5.3 Codex OpenAI

45.8

Rank #69 Reported

Summary

  • They share 3 benchmarks with published results for both. Gemini 2.5 Flash-Lite scores higher in 0 categories and GPT-5.3 Codex in 2 categories; 2 gaps are clear of the uncertainty.
  • The widest gap is in agentic & tool use, where GPT-5.3 Codex leads 48.0 to 28.0.
  • The biggest single-benchmark swing is WeirdML: 35.2% for Gemini 2.5 Flash-Lite and 79.3% for GPT-5.3 Codex.
  • Gemini 2.5 Flash-Lite is cheaper at $0.10 / $0.40 per million input/output tokens, against $1.75 / $14 for GPT-5.3 Codex.
  • Gemini 2.5 Flash-Lite accepts more context: 1.05M tokens versus 400K.

Side by side

Gemini 2.5 Flash-LiteGPT-5.3 Codex
ProviderGoogleOpenAI
Noometry Index37.045.8
Released2025-06-172026-02-05
WeightsProprietaryProprietary
Context window1.05M400K
Max output66K128K
Input $ / M tokens$0.10$1.75
Output $ / M tokens$0.40$14
Results tracked338

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

Category by category

Coding GPT-5.3 Codex leads

Gemini 2.5 Flash-Lite: 38.5 (#173), GPT-5.3 Codex: 48.6 (#56)

BenchmarkGemini 2.5 Flash-LiteGPT-5.3 Codex
WeirdML35.2%79.3%
ALE-Bench325.91,655
SWE-bench Verified—74.8%
LMArena WebDev—1409
LMArena Coding1373—

Agentic & Tool Use GPT-5.3 Codex leads

Gemini 2.5 Flash-Lite: 28.0 (#96), GPT-5.3 Codex: 48.0 (#9)

BenchmarkGemini 2.5 Flash-LiteGPT-5.3 Codex
Terminal-Bench—78.4%
Berkeley Function Calling Leaderboard36.9%—
METR Time Horizons—74.5%
Vending-Bench 2—5,940

Reasoning Not comparable

Gemini 2.5 Flash-Lite: 22.2 (#205), GPT-5.3 Codex: —

BenchmarkGemini 2.5 Flash-LiteGPT-5.3 Codex
Epoch Capabilities Index133.94156.77
Kagi LLM Benchmark40.5%—
LMArena Hard Prompts1377—
DTBench62.8%—
LMCA18.1%—

Math Not comparable

Gemini 2.5 Flash-Lite: 38.0 (#144), GPT-5.3 Codex: —

BenchmarkGemini 2.5 Flash-LiteGPT-5.3 Codex
Omni-MATH48%—
LMArena Math1373—

Knowledge Not comparable

Gemini 2.5 Flash-Lite: 32.5 (#210), GPT-5.3 Codex: —

BenchmarkGemini 2.5 Flash-LiteGPT-5.3 Codex
MMLU-Pro53.7%—
Vectara Hallucination Rate3.3%—
GPQA (HELM)30.9%—
LMArena Expert1373—

Multimodal Not comparable

Gemini 2.5 Flash-Lite: 29.1 (#114), GPT-5.3 Codex: —

BenchmarkGemini 2.5 Flash-LiteGPT-5.3 Codex
LMArena Vision1198—
VPCT30%—

Multilingual Not comparable

Gemini 2.5 Flash-Lite: 49.3 (#134), GPT-5.3 Codex: —

BenchmarkGemini 2.5 Flash-LiteGPT-5.3 Codex
LMArena Non-English1369—
LMArena Chinese1404—
LMArena French1388—
LMArena German1389—
LMArena Japanese1359—
LMArena Korean1360—
LMArena Russian1373—
LMArena Spanish1396—

Instruction Following Not comparable

Gemini 2.5 Flash-Lite: 70.0 (#168), GPT-5.3 Codex: —

BenchmarkGemini 2.5 Flash-LiteGPT-5.3 Codex
IFEval81%—
LMArena Instruction Following1367—

Long Context Not comparable

Gemini 2.5 Flash-Lite: 33.3 (#262), GPT-5.3 Codex: —

BenchmarkGemini 2.5 Flash-LiteGPT-5.3 Codex
Fiction.LiveBench47.2%—
LMArena Longer Query1373—

Writing & Preference Not comparable

Gemini 2.5 Flash-Lite: 56.8 (#135), GPT-5.3 Codex: —

BenchmarkGemini 2.5 Flash-LiteGPT-5.3 Codex
LMArena Text1379—
LMArena Creative Writing1367—
WildBench81.8%—
LMArena Multi-Turn1366—

Frequently asked questions

Is Gemini 2.5 Flash-Lite better than GPT-5.3 Codex?

GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 37.0 on the Noometry Index. Gemini 2.5 Flash-Lite costs 27× less per token, which makes it the better buy when GPT-5.3 Codex's lead doesn't matter for your workload.

Which is cheaper, Gemini 2.5 Flash-Lite or GPT-5.3 Codex?

Gemini 2.5 Flash-Lite is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; GPT-5.3 Codex lists at $1.75 and $14.

Is Gemini 2.5 Flash-Lite or GPT-5.3 Codex better for coding?

GPT-5.3 Codex scores higher on coding benchmarks: 48.6 versus 38.5 in the Noometry coding category.

Which has the bigger context window?

Gemini 2.5 Flash-Lite does, with 1.05M tokens against 400K.

How many benchmarks do Gemini 2.5 Flash-Lite and GPT-5.3 Codex share?

3 benchmarks have published results for both models. Gemini 2.5 Flash-Lite has 33 scored results on Noometry and GPT-5.3 Codex has 8.

Related comparisons

Go deeper