Noometry

Model comparison

Claude Sonnet 4.5 vs Gemini 3 Flash Preview

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 44.1 on the Noometry Index.

Last verified . 53 shared benchmarks.

Claude Sonnet 4.5 Anthropic

44.1

Rank #81 Confirmed

Gemini 3 Flash Preview Google

52.3

Rank #40 Confirmed

Summary

  • They share 53 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 2 categories and Gemini 3 Flash Preview in 8 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3 Flash Preview leads 49.2 to 26.9.
  • The biggest single-benchmark swing is NYT Connections (extended): 37.3% for Claude Sonnet 4.5 and 83.1% for Gemini 3 Flash Preview.
  • Gemini 3 Flash Preview is cheaper at $0.50 / $3 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
  • Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 200K.

Side by side

Claude Sonnet 4.5Gemini 3 Flash Preview
ProviderAnthropicGoogle
Noometry Index44.152.3
Released2025-09-292025-12-17
WeightsProprietaryProprietary
Context window200K1.05M
Max output64K66K
Input $ / M tokens$3$0.50
Output $ / M tokens$15$3
Results tracked7359

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

Category by category

Coding Gemini 3 Flash Preview leads

Claude Sonnet 4.5: 47.3 (#61), Gemini 3 Flash Preview: 50.9 (#42)

BenchmarkClaude Sonnet 4.5Gemini 3 Flash Preview
SWE-bench Verified71.3%75.4%
SWE-bench Verified (bash only)71.4%75.8%
LMArena WebDev13931439
SWE-bench Multilingual67%72.7%
GSO14.7%9.8%
WeirdML47.7%61.6%
LMArena Coding14891460
ALE-Bench796.151,367
SciCode44.7%—
AlgoTune1.52—

Agentic & Tool Use Too close to call

Claude Sonnet 4.5: 38.3 (#32), Gemini 3 Flash Preview: 38.7 (#29)

BenchmarkClaude Sonnet 4.5Gemini 3 Flash Preview
Terminal-Bench46.5%64.3%
τ²-bench Airline72%82.5%
τ²-bench Banking25.3%27.3%
τ²-bench Retail72.4%76.8%
τ²-bench Telecom84.9%91.2%
DeepResearch Bench52.6%49.8%
LMArena Search11591198
Vending-Bench 23,8393,635
Berkeley Function Calling Leaderboard73.2%—
GDPval42.5%—
Remote Labor Index2.1%—
Cybench60%—
OSWorld62.9%—
BALROG—48.1%
GDP.pdf—10%
METR Time Horizons67.4%—

Reasoning Gemini 3 Flash Preview leads

Claude Sonnet 4.5: 26.9 (#125), Gemini 3 Flash Preview: 49.2 (#37)

BenchmarkClaude Sonnet 4.5Gemini 3 Flash Preview
ARC-AGI-213.6%33.6%
SimpleBench54.3%61.1%
NYT Connections (extended)37.3%83.1%
ARC-AGI-163.7%84.7%
Chess Puzzles12%40%
LMArena Hard Prompts14621465
Mystery Game Puzzles17%26%
DTBench83.2%89.1%
LMCA38.8%43.1%
Epoch Capabilities Index146.84151.8
ForecastBench61.958.5
Kagi LLM Benchmark57.9%—
CritPt1.1%—
EnigmaEval6%—
EBR-Bench2.4%—

Math Gemini 3 Flash Preview leads

Claude Sonnet 4.5: 32.3 (#216), Gemini 3 Flash Preview: 51.7 (#55)

BenchmarkClaude Sonnet 4.5Gemini 3 Flash Preview
FrontierMath (Tiers 1-3)23.9%51.2%
FrontierMath Tier 42.4%17.1%
OTIS Mock AIME 2024-202577.8%95.6%
ProofBench19%15%
LMArena Math14491473
FrontierMath (Feb 2025 set)15.2%35.6%
FrontierMath Tier 4 (v1)4.2%4.2%
MathArena Final-Answer Competitions—67.6%
Omni-MATH55.3%—
MATH Level 597.7%—

Knowledge Gemini 3 Flash Preview leads

Claude Sonnet 4.5: 48.4 (#76), Gemini 3 Flash Preview: 58.8 (#33)

BenchmarkClaude Sonnet 4.5Gemini 3 Flash Preview
GPQA Diamond82.3%89.4%
SimpleQA Verified30.7%66.8%
Vectara Hallucination Rate12%13.5%
LMArena Expert14821462
Humanity's Last Exam13.7%—
MMLU-Pro86.9%—
GPQA (HELM)68.6%—

Multimodal Gemini 3 Flash Preview leads

Claude Sonnet 4.5: 34.8 (#89), Gemini 3 Flash Preview: 45.5 (#16)

BenchmarkClaude Sonnet 4.5Gemini 3 Flash Preview
VPCT39.8%72.6%
LMArena Document14501413
LMArena Vision—1285
GeoBench—88%
Blueprint-Bench 2—0%

Multilingual Gemini 3 Flash Preview leads

Claude Sonnet 4.5: 53.4 (#69), Gemini 3 Flash Preview: 55.7 (#27)

BenchmarkClaude Sonnet 4.5Gemini 3 Flash Preview
LMArena Non-English14251458
LMArena Chinese14591511
LMArena French14581477
LMArena German14271497
LMArena Japanese13901489
LMArena Korean14031443
LMArena Russian14371480
LMArena Spanish14571469

Instruction Following Too close to call

Claude Sonnet 4.5: 75.0 (#78), Gemini 3 Flash Preview: 75.7 (#56)

BenchmarkClaude Sonnet 4.5Gemini 3 Flash Preview
LMArena Instruction Following14591437
IFEval85%—

Long Context Too close to call

Claude Sonnet 4.5: 45.2 (#46), Gemini 3 Flash Preview: 44.4 (#67)

BenchmarkClaude Sonnet 4.5Gemini 3 Flash Preview
LMArena Longer Query14761452

Writing & Preference Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 66.5 (#34), Gemini 3 Flash Preview: 65.5 (#45)

BenchmarkClaude Sonnet 4.5Gemini 3 Flash Preview
LMArena Text14391466
LMArena Creative Writing14421457
LMArena Multi-Turn14651471
EQ-Bench Creative Writing1678—
WildBench85.4%—

Frequently asked questions

Is Claude Sonnet 4.5 better than Gemini 3 Flash Preview?

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 44.1 on the Noometry Index.

Which is cheaper, Claude Sonnet 4.5 or Gemini 3 Flash Preview?

Gemini 3 Flash Preview is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.

Is Claude Sonnet 4.5 or Gemini 3 Flash Preview better for coding?

Gemini 3 Flash Preview scores higher on coding benchmarks: 50.9 versus 47.3 in the Noometry coding category.

Which has the bigger context window?

Gemini 3 Flash Preview does, with 1.05M tokens against 200K.

How many benchmarks do Claude Sonnet 4.5 and Gemini 3 Flash Preview share?

53 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Gemini 3 Flash Preview has 59.

Related comparisons

Go deeper