Noometry

Model comparison

Gemini 2.5 Flash vs Gemini 3 Deep Think

Gemini 2.5 Flash has enough public results to be ranked (#170); Gemini 3 Deep Think does not yet, so treat this comparison as directional.

Last verified . 3 shared benchmarks.

Gemini 2.5 Flash Google

39.3

Rank #170 Confirmed

Gemini 3 Deep Think Google

58.3

Unranked Sparse

Summary

  • They share 3 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 0 categories and Gemini 3 Deep Think in 1 category; one gap is clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3 Deep Think leads 70.2 to 18.1.
  • The biggest single-benchmark swing is ARC-AGI-2: 2.5% for Gemini 2.5 Flash and 84.6% for Gemini 3 Deep Think.

Side by side

Gemini 2.5 FlashGemini 3 Deep Think
ProviderGoogleGoogle
Noometry Index39.358.3
Released2025-04-172026-02-12
WeightsProprietaryProprietary
Context window1.05M—
Max output66K—
Input $ / M tokens$0.30—
Output $ / M tokens$2.50—
Results tracked543

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

Category by category

Coding Not comparable

Gemini 2.5 Flash: 35.8 (#220), Gemini 3 Deep Think: —

BenchmarkGemini 2.5 FlashGemini 3 Deep Think
SWE-bench Verified (bash only)28.7%—
Aider Polyglot55.1%—
WeirdML41.9%—
LMArena Coding1424—
ALE-Bench661.88—

Agentic & Tool Use Not comparable

Gemini 2.5 Flash: 30.8 (#74), Gemini 3 Deep Think: —

BenchmarkGemini 2.5 FlashGemini 3 Deep Think
Terminal-Bench17.1%—
Berkeley Function Calling Leaderboard56.2%—
TheAgentCompany41.1%—
BALROG33.5%—
Vending-Bench 2548.84—

Reasoning Gemini 3 Deep Think leads

Gemini 2.5 Flash: 18.1 (#286), Gemini 3 Deep Think: 70.2 (#14)

BenchmarkGemini 2.5 FlashGemini 3 Deep Think
ARC-AGI-22.5%84.6%
ARC-AGI-133.3%96%
CritPt1.1%25.7%
SimpleBench41.2%—
Kagi LLM Benchmark56.8%—
EnigmaEval2.7%—
LMArena Hard Prompts1422—
DTBench76.5%—
LMCA27.5%—
Epoch Capabilities Index143.03—
ForecastBench60.6—

Math Not comparable

Gemini 2.5 Flash: 39.9 (#98), Gemini 3 Deep Think: —

BenchmarkGemini 2.5 FlashGemini 3 Deep Think
OTIS Mock AIME 2024-202573.1%—
Omni-MATH38.5%—
LMArena Math1415—
FrontierMath (Feb 2025 set)4.8%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Not comparable

Gemini 2.5 Flash: 36.4 (#168), Gemini 3 Deep Think: —

BenchmarkGemini 2.5 FlashGemini 3 Deep Think
Humanity's Last Exam12.1%—
MMLU-Pro63.9%—
Confabulations16.8%—
Vectara Hallucination Rate7.8%—
GPQA (HELM)39%—
LMArena Expert1426—

Multimodal Not comparable

Gemini 2.5 Flash: 41.8 (#32), Gemini 3 Deep Think: —

BenchmarkGemini 2.5 FlashGemini 3 Deep Think
LMArena Vision1253—
GeoBench76%—
VPCT46.2%—
SpatialViz-Bench36.9%—

Multilingual Not comparable

Gemini 2.5 Flash: 52.3 (#88), Gemini 3 Deep Think: —

BenchmarkGemini 2.5 FlashGemini 3 Deep Think
LMArena Non-English1409—
LMArena Chinese1450—
LMArena French1433—
LMArena German1418—
LMArena Japanese1405—
LMArena Korean1385—
LMArena Russian1415—
LMArena Spanish1421—

Instruction Following Not comparable

Gemini 2.5 Flash: 75.7 (#54), Gemini 3 Deep Think: —

BenchmarkGemini 2.5 FlashGemini 3 Deep Think
IFEval89.8%—
LMArena Instruction Following1405—

Long Context Not comparable

Gemini 2.5 Flash: 47.5 (#17), Gemini 3 Deep Think: —

BenchmarkGemini 2.5 FlashGemini 3 Deep Think
Fiction.LiveBench77.8%—
LMArena Longer Query1419—

Writing & Preference Not comparable

Gemini 2.5 Flash: 53.8 (#157), Gemini 3 Deep Think: —

BenchmarkGemini 2.5 FlashGemini 3 Deep Think
LMArena Text1417—
LMArena Creative Writing1400—
Short-Story Creative Writing76.5%—
EQ-Bench Creative Writing1137—
WildBench81.7%—
LMArena Multi-Turn1408—

Frequently asked questions

Is Gemini 2.5 Flash better than Gemini 3 Deep Think?

Gemini 2.5 Flash has enough public results to be ranked (#170); Gemini 3 Deep Think does not yet, so treat this comparison as directional.

How many benchmarks do Gemini 2.5 Flash and Gemini 3 Deep Think share?

3 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Gemini 3 Deep Think has 3.

Related comparisons

Go deeper