Noometry

Model comparison

Claude Sonnet 4.5 vs Gemini 2.5 Flash

Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 39.3 on the Noometry Index. Gemini 2.5 Flash costs 7.1× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

Last verified . 45 shared benchmarks.

Claude Sonnet 4.5 Anthropic

44.1

Rank #81 Confirmed

Gemini 2.5 Flash Google

39.3

Rank #170 Confirmed

Summary

  • They share 45 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 6 categories and Gemini 2.5 Flash in 4 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Claude Sonnet 4.5 leads 66.5 to 53.8.
  • The biggest single-benchmark swing is SWE-bench Verified (bash only): 71.4% for Claude Sonnet 4.5 and 28.7% for Gemini 2.5 Flash.
  • Gemini 2.5 Flash is cheaper at $0.30 / $2.50 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
  • Gemini 2.5 Flash accepts more context: 1.05M tokens versus 200K.

Side by side

Claude Sonnet 4.5Gemini 2.5 Flash
ProviderAnthropicGoogle
Noometry Index44.139.3
Released2025-09-292025-04-17
WeightsProprietaryProprietary
Context window200K1.05M
Max output64K66K
Input $ / M tokens$3$0.30
Output $ / M tokens$15$2.50
Results tracked7354

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

Category by category

Coding Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 47.3 (#61), Gemini 2.5 Flash: 35.8 (#220)

BenchmarkClaude Sonnet 4.5Gemini 2.5 Flash
SWE-bench Verified (bash only)71.4%28.7%
WeirdML47.7%41.9%
LMArena Coding14891424
ALE-Bench796.15661.88
SWE-bench Verified71.3%—
Aider Polyglot—55.1%
LMArena WebDev1393—
SWE-bench Multilingual67%—
SciCode44.7%—
GSO14.7%—
AlgoTune1.52—

Agentic & Tool Use Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 38.3 (#32), Gemini 2.5 Flash: 30.8 (#74)

BenchmarkClaude Sonnet 4.5Gemini 2.5 Flash
Terminal-Bench46.5%17.1%
Berkeley Function Calling Leaderboard73.2%56.2%
Vending-Bench 23,839548.84
GDPval42.5%—
Remote Labor Index2.1%—
TheAgentCompany—41.1%
τ²-bench Airline72%—
τ²-bench Banking25.3%—
τ²-bench Retail72.4%—
τ²-bench Telecom84.9%—
Cybench60%—
DeepResearch Bench52.6%—
OSWorld62.9%—
BALROG—33.5%
LMArena Search1159—
METR Time Horizons67.4%—

Reasoning Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 26.9 (#125), Gemini 2.5 Flash: 18.1 (#286)

BenchmarkClaude Sonnet 4.5Gemini 2.5 Flash
ARC-AGI-213.6%2.5%
SimpleBench54.3%41.2%
Kagi LLM Benchmark57.9%56.8%
ARC-AGI-163.7%33.3%
CritPt1.1%1.1%
EnigmaEval6%2.7%
LMArena Hard Prompts14621422
DTBench83.2%76.5%
LMCA38.8%27.5%
Epoch Capabilities Index146.84143.03
ForecastBench61.960.6
NYT Connections (extended)37.3%—
Chess Puzzles12%—
EBR-Bench2.4%—
Mystery Game Puzzles17%—

Math Gemini 2.5 Flash leads

Claude Sonnet 4.5: 32.3 (#216), Gemini 2.5 Flash: 39.9 (#98)

BenchmarkClaude Sonnet 4.5Gemini 2.5 Flash
OTIS Mock AIME 2024-202577.8%73.1%
Omni-MATH55.3%38.5%
LMArena Math14491415
FrontierMath (Feb 2025 set)15.2%4.8%
FrontierMath Tier 4 (v1)4.2%4.2%
FrontierMath (Tiers 1-3)23.9%—
FrontierMath Tier 42.4%—
ProofBench19%—
MATH Level 597.7%—

Knowledge Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 48.4 (#76), Gemini 2.5 Flash: 36.4 (#168)

BenchmarkClaude Sonnet 4.5Gemini 2.5 Flash
Humanity's Last Exam13.7%12.1%
MMLU-Pro86.9%63.9%
Vectara Hallucination Rate12%7.8%
GPQA (HELM)68.6%39%
LMArena Expert14821426
GPQA Diamond82.3%—
SimpleQA Verified30.7%—
Confabulations—16.8%

Multimodal Gemini 2.5 Flash leads

Claude Sonnet 4.5: 34.8 (#89), Gemini 2.5 Flash: 41.8 (#32)

BenchmarkClaude Sonnet 4.5Gemini 2.5 Flash
VPCT39.8%46.2%
LMArena Vision—1253
GeoBench—76%
LMArena Document1450—
SpatialViz-Bench—36.9%

Multilingual Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 53.4 (#69), Gemini 2.5 Flash: 52.3 (#88)

BenchmarkClaude Sonnet 4.5Gemini 2.5 Flash
LMArena Non-English14251409
LMArena Chinese14591450
LMArena French14581433
LMArena German14271418
LMArena Japanese13901405
LMArena Korean14031385
LMArena Russian14371415
LMArena Spanish14571421

Instruction Following Too close to call

Claude Sonnet 4.5: 75.0 (#78), Gemini 2.5 Flash: 75.7 (#54)

BenchmarkClaude Sonnet 4.5Gemini 2.5 Flash
IFEval85%89.8%
LMArena Instruction Following14591405

Long Context Gemini 2.5 Flash leads

Claude Sonnet 4.5: 45.2 (#46), Gemini 2.5 Flash: 47.5 (#17)

BenchmarkClaude Sonnet 4.5Gemini 2.5 Flash
LMArena Longer Query14761419
Fiction.LiveBench—77.8%

Writing & Preference Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 66.5 (#34), Gemini 2.5 Flash: 53.8 (#157)

BenchmarkClaude Sonnet 4.5Gemini 2.5 Flash
LMArena Text14391417
LMArena Creative Writing14421400
EQ-Bench Creative Writing16781137
WildBench85.4%81.7%
LMArena Multi-Turn14651408
Short-Story Creative Writing—76.5%

Frequently asked questions

Is Claude Sonnet 4.5 better than Gemini 2.5 Flash?

Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 39.3 on the Noometry Index. Gemini 2.5 Flash costs 7.1× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

Which is cheaper, Claude Sonnet 4.5 or Gemini 2.5 Flash?

Gemini 2.5 Flash is cheaper. It lists at $0.30 per million input tokens and $2.50 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.

Is Claude Sonnet 4.5 or Gemini 2.5 Flash better for coding?

Claude Sonnet 4.5 scores higher on coding benchmarks: 47.3 versus 35.8 in the Noometry coding category.

Which has the bigger context window?

Gemini 2.5 Flash does, with 1.05M tokens against 200K.

How many benchmarks do Claude Sonnet 4.5 and Gemini 2.5 Flash share?

45 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Gemini 2.5 Flash has 54.

Related comparisons

Go deeper