Noometry

Model comparison

Gemini 2.5 Flash vs GPT-5.5

GPT-5.5 is the stronger model overall, scoring 63.4 to 39.3 on the Noometry Index. Gemini 2.5 Flash costs 13× less per token, which makes it the better buy when GPT-5.5's lead doesn't matter for your workload.

Last verified . 36 shared benchmarks.

Gemini 2.5 Flash Google

39.3

Rank #170 Confirmed

GPT-5.5 OpenAI

63.4

Rank #9 Confirmed

Summary

  • They share 36 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 0 categories and GPT-5.5 in 10 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where GPT-5.5 leads 72.8 to 18.1.
  • The biggest single-benchmark swing is ARC-AGI-2: 2.5% for Gemini 2.5 Flash and 85% for GPT-5.5.
  • Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $5 / $30 for GPT-5.5.
  • GPT-5.5 accepts more context: 1.05M tokens versus 1.05M.

Side by side

Gemini 2.5 FlashGPT-5.5
ProviderGoogleOpenAI
Noometry Index39.363.4
Released2025-04-172026-04-23
WeightsProprietaryProprietary
Context window1.05M1.05M
Max output66K128K
Input $ / M tokens$0.30$5
Output $ / M tokens$2.50$30
Results tracked5471

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

Category by category

Coding GPT-5.5 leads

Gemini 2.5 Flash: 35.8 (#220), GPT-5.5: 58.2 (#17)

BenchmarkGemini 2.5 FlashGPT-5.5
WeirdML41.9%84.9%
LMArena Coding14241494
ALE-Bench661.881,943
SWE-bench Verified—80.6%
DeepSWE—67%
FrontierCode—43%
SWE-bench Verified (bash only)28.7%—
Aider Polyglot55.1%—
LMArena WebDev—1513
SciCode—56.1%
GSO—40.2%
MirrorCode—10%

Agentic & Tool Use GPT-5.5 leads

Gemini 2.5 Flash: 30.8 (#74), GPT-5.5: 50.7 (#6)

BenchmarkGemini 2.5 FlashGPT-5.5
Terminal-Bench17.1%84.7%
Vending-Bench 2548.847,524
APEX-Agents—55.1%
Berkeley Function Calling Leaderboard56.2%—
OSWorld 2.0—13%
Remote Labor Index—6.3%
TheAgentCompany41.1%—
τ²-bench Banking—44.6%
DeepResearch Bench—54%
PostTrainBench—27.2%
BALROG33.5%—
ExploitBench—47.4%
GBAEval—53.2%
GDP.pdf—26%
LMArena Search—1242

Reasoning GPT-5.5 leads

Gemini 2.5 Flash: 18.1 (#286), GPT-5.5: 72.8 (#11)

BenchmarkGemini 2.5 FlashGPT-5.5
ARC-AGI-22.5%85%
SimpleBench41.2%69%
Kagi LLM Benchmark56.8%88.8%
ARC-AGI-133.3%95%
CritPt1.1%27.1%
LMArena Hard Prompts14221489
DTBench76.5%96%
LMCA27.5%54.3%
Epoch Capabilities Index143.03159.1
ForecastBench60.660.6
NYT Connections (extended)—96.2%
Chess Puzzles—54%
EnigmaEval2.7%—
EBR-Bench—34.3%
Mystery Game Puzzles—56%
Surface Evolver Bench—88.1%
Bench to the Future 3—0.14

Math GPT-5.5 leads

Gemini 2.5 Flash: 39.9 (#98), GPT-5.5: 81.7 (#11)

BenchmarkGemini 2.5 FlashGPT-5.5
OTIS Mock AIME 2024-202573.1%100%
LMArena Math14151486
FrontierMath (Feb 2025 set)4.8%51.7%
FrontierMath Tier 4 (v1)4.2%35.4%
FrontierMath (Tiers 1-3)—85.3%
FrontierMath Tier 4—72.5%
MathArena Final-Answer Competitions—94.3%
ProofBench—50%
Omni-MATH38.5%—
FrontierMath Erdős—0%

Knowledge GPT-5.5 leads

Gemini 2.5 Flash: 36.4 (#168), GPT-5.5: 64.4 (#17)

BenchmarkGemini 2.5 FlashGPT-5.5
Vectara Hallucination Rate7.8%9.3%
LMArena Expert14261508
GPQA Diamond—94%
Humanity's Last Exam12.1%—
SimpleQA Verified—63%
MMLU-Pro63.9%—
Confabulations16.8%—
GPQA (HELM)39%—

Multimodal GPT-5.5 leads

Gemini 2.5 Flash: 41.8 (#32), GPT-5.5: 46.9 (#12)

BenchmarkGemini 2.5 FlashGPT-5.5
LMArena Vision12531297
GeoBench76%—
VPCT46.2%—
Blueprint-Bench 2—36.2%
Furniture Assembly—44.2%
LMArena Document—1486
SpatialViz-Bench36.9%—

Multilingual GPT-5.5 leads

Gemini 2.5 Flash: 52.3 (#88), GPT-5.5: 56.4 (#20)

BenchmarkGemini 2.5 FlashGPT-5.5
LMArena Non-English14091467
LMArena Chinese14501533
LMArena French14331486
LMArena German14181480
LMArena Japanese14051498
LMArena Korean13851460
LMArena Russian14151473
LMArena Spanish14211468

Instruction Following GPT-5.5 leads

Gemini 2.5 Flash: 75.7 (#54), GPT-5.5: 77.5 (#18)

BenchmarkGemini 2.5 FlashGPT-5.5
LMArena Instruction Following14051479
IFEval89.8%—

Long Context Too close to call

Gemini 2.5 Flash: 47.5 (#17), GPT-5.5: 48.3 (#12)

BenchmarkGemini 2.5 FlashGPT-5.5
LMArena Longer Query14191484
Fiction.LiveBench77.8%—
CL-bench Life—22.2%

Writing & Preference GPT-5.5 leads

Gemini 2.5 Flash: 53.8 (#157), GPT-5.5: 72.7 (#13)

BenchmarkGemini 2.5 FlashGPT-5.5
LMArena Text14171472
LMArena Creative Writing14001455
EQ-Bench Creative Writing11371844
LMArena Multi-Turn14081476
Short-Story Creative Writing76.5%—
WildBench81.7%—
EQ-Bench 4—1315

Frequently asked questions

Is Gemini 2.5 Flash better than GPT-5.5?

GPT-5.5 is the stronger model overall, scoring 63.4 to 39.3 on the Noometry Index. Gemini 2.5 Flash costs 13× less per token, which makes it the better buy when GPT-5.5's lead doesn't matter for your workload.

Which is cheaper, Gemini 2.5 Flash or GPT-5.5?

Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; GPT-5.5 lists at $5 and $30.

Is Gemini 2.5 Flash or GPT-5.5 better for coding?

GPT-5.5 scores higher on coding benchmarks: 58.2 versus 35.8 in the Noometry coding category.

Which has the bigger context window?

GPT-5.5 does, with 1.05M tokens against 1.05M.

How many benchmarks do Gemini 2.5 Flash and GPT-5.5 share?

36 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and GPT-5.5 has 71.

Related comparisons

Go deeper