Noometry

Model comparison

Gemini 3.1 Flash Lite vs GPT-4.5

Gemini 3.1 Flash Lite is the stronger model overall, scoring 40.8 to 37.2 on the Noometry Index.

Last verified . 24 shared benchmarks.

Gemini 3.1 Flash Lite Google

40.8

Rank #144 Confirmed

GPT-4.5 OpenAI

37.2

Rank #208 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Gemini 3.1 Flash Lite scores higher in 8 categories and GPT-4.5 in 2 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Gemini 3.1 Flash Lite leads 41.9 to 32.5.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 80% for Gemini 3.1 Flash Lite and 37.8% for GPT-4.5.

Side by side

Gemini 3.1 Flash LiteGPT-4.5
ProviderGoogleOpenAI
Noometry Index40.837.2
Released2026-03-032025-02-27
WeightsProprietaryProprietary
Context window1.05M—
Max output66K—
Input $ / M tokens$0.25—
Output $ / M tokens$1.50—
Results tracked3842

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

Category by category

Coding GPT-4.5 leads

Gemini 3.1 Flash Lite: 37.8 (#188), GPT-4.5: 42.2 (#109)

BenchmarkGemini 3.1 Flash LiteGPT-4.5
WeirdML52.2%39.4%
LMArena Coding14001396
Aider Polyglot—44.9%
LMArena WebDev1256—
SciCode41.9%—
LiveBench Coding—75.2%
ALE-Bench797.73—

Agentic & Tool Use Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 30.2 (#79), GPT-4.5: 27.9 (#97)

BenchmarkGemini 3.1 Flash LiteGPT-4.5
Cybench—17.5%
DeepResearch Bench37.3%—

Reasoning Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 22.9 (#186), GPT-4.5: 13.9 (#330)

BenchmarkGemini 3.1 Flash LiteGPT-4.5
EnigmaEval3%3.2%
LMArena Hard Prompts14071403
Epoch Capabilities Index144.47136.74
ForecastBench54.461.7
ARC-AGI-2—0.8%
SimpleBench—34.5%
Kagi LLM Benchmark67.2%—
NYT Connections (extended)8.2%—
ARC-AGI-1—10.3%
CritPt1.1%—
Chess Puzzles25%—
Thematic Generalization63.3%—
LiveBench Reasoning—71.1%
DTBench76.8%—
LiveBench Data Analysis—64.3%
LMCA35%—
LiveBench—69%

Math Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 40.7 (#90), GPT-4.5: 32.6 (#211)

BenchmarkGemini 3.1 Flash LiteGPT-4.5
OTIS Mock AIME 2024-202580%37.8%
LMArena Math14281412
FrontierMath (Tiers 1-3)27.7%—
LiveBench Math—69.3%
MATH Level 5—78.6%

Knowledge Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 41.9 (#104), GPT-4.5: 32.5 (#211)

BenchmarkGemini 3.1 Flash LiteGPT-4.5
GPQA Diamond81.8%68.7%
Humanity's Last Exam8.6%5.4%
LMArena Expert13981394
Confabulations—13.6%
Vectara Hallucination Rate8.2%—

Multimodal Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 39.4 (#60), GPT-4.5: 37.6 (#71)

BenchmarkGemini 3.1 Flash LiteGPT-4.5
LMArena Vision12401195
VPCT—45%

Multilingual Too close to call

Gemini 3.1 Flash Lite: 52.3 (#86), GPT-4.5: 52.5 (#83)

BenchmarkGemini 3.1 Flash LiteGPT-4.5
LMArena Non-English14111413
LMArena Chinese14611421
LMArena French14241418
LMArena German14291457
LMArena Japanese14131416
LMArena Korean13921392
LMArena Russian14201419
LMArena Spanish1421—

Instruction Following Too close to call

Gemini 3.1 Flash Lite: 72.7 (#131), GPT-4.5: 72.6 (#134)

BenchmarkGemini 3.1 Flash LiteGPT-4.5
LMArena Instruction Following13771404
LiveBench Instruction Following—72.3%

Long Context Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 42.5 (#122), GPT-4.5: 40.4 (#155)

BenchmarkGemini 3.1 Flash LiteGPT-4.5
LMArena Longer Query13941406
Fiction.LiveBench—63.9%

Writing & Preference Gemini 3.1 Flash Lite leads

Gemini 3.1 Flash Lite: 60.9 (#94), GPT-4.5: 56.9 (#134)

BenchmarkGemini 3.1 Flash LiteGPT-4.5
LMArena Text14161417
LMArena Creative Writing14011394
LMArena Multi-Turn14171444
Short-Story Creative Writing—75.6%
EQ-Bench Creative Writing—1258
LiveBench Language—61.5%

Frequently asked questions

Is Gemini 3.1 Flash Lite better than GPT-4.5?

Gemini 3.1 Flash Lite is the stronger model overall, scoring 40.8 to 37.2 on the Noometry Index.

Is Gemini 3.1 Flash Lite or GPT-4.5 better for coding?

GPT-4.5 scores higher on coding benchmarks: 42.2 versus 37.8 in the Noometry coding category.

How many benchmarks do Gemini 3.1 Flash Lite and GPT-4.5 share?

24 benchmarks have published results for both models. Gemini 3.1 Flash Lite has 38 scored results on Noometry and GPT-4.5 has 42.

Related comparisons

Go deeper