Noometry

Model comparison

Claude Sonnet 5 vs Gemini 3 Flash Preview

Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 52.3 on the Noometry Index. Gemini 3 Flash Preview costs 3.6× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.

Last verified . 40 shared benchmarks.

Claude Sonnet 5 Anthropic

54.6

Rank #29 Confirmed

Gemini 3 Flash Preview Google

52.3

Rank #40 Confirmed

Summary

  • They share 40 benchmarks with published results for both. Claude Sonnet 5 scores higher in 6 categories and Gemini 3 Flash Preview in 4 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Sonnet 5 leads 66.2 to 51.7.
  • The biggest single-benchmark swing is ProofBench: 77% for Claude Sonnet 5 and 15% for Gemini 3 Flash Preview.
  • Gemini 3 Flash Preview is cheaper at $0.50 / $3 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.
  • Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 1M.

Side by side

Claude Sonnet 5Gemini 3 Flash Preview
ProviderAnthropicGoogle
Noometry Index54.652.3
Released2026-06-292025-12-17
WeightsProprietaryProprietary
Context window1M1.05M
Max output128K66K
Input $ / M tokens$2$0.50
Output $ / M tokens$10$3
Results tracked5159

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

Category by category

Coding Claude Sonnet 5 leads

Claude Sonnet 5: 55.5 (#26), Gemini 3 Flash Preview: 50.9 (#42)

BenchmarkClaude Sonnet 5Gemini 3 Flash Preview
LMArena WebDev15411439
GSO37.3%9.8%
WeirdML68.8%61.6%
LMArena Coding14831460
ALE-Bench1,4631,367
SWE-bench Verified—75.4%
DeepSWE53.8%—
FrontierCode42.7%—
SWE-bench Verified (bash only)—75.8%
CursorBench34.1%—
SWE-bench Multilingual—72.7%
SciCode54.3%—

Agentic & Tool Use Claude Sonnet 5 leads

Claude Sonnet 5: 42.8 (#18), Gemini 3 Flash Preview: 38.7 (#29)

BenchmarkClaude Sonnet 5Gemini 3 Flash Preview
LMArena Search11941198
Vending-Bench 26,3783,635
Terminal-Bench—64.3%
APEX-Agents54.5%—
τ²-bench Airline—82.5%
τ²-bench Banking—27.3%
τ²-bench Retail—76.8%
τ²-bench Telecom—91.2%
DeepResearch Bench—49.8%
BALROG—48.1%
GBAEval65.3%—
GDP.pdf—10%

Reasoning Too close to call

Claude Sonnet 5: 49.1 (#39), Gemini 3 Flash Preview: 49.2 (#37)

BenchmarkClaude Sonnet 5Gemini 3 Flash Preview
SimpleBench60.6%61.1%
NYT Connections (extended)75.1%83.1%
Chess Puzzles35%40%
LMArena Hard Prompts14611465
Mystery Game Puzzles35%26%
DTBench92.5%89.1%
LMCA50%43.1%
Epoch Capabilities Index156.21151.8
ForecastBench61.158.5
ARC-AGI-2—33.6%
ARC-AGI-1—84.7%
CritPt16.9%—
Surface Evolver Bench60%—
Bench to the Future 30.14—

Math Claude Sonnet 5 leads

Claude Sonnet 5: 66.2 (#27), Gemini 3 Flash Preview: 51.7 (#55)

BenchmarkClaude Sonnet 5Gemini 3 Flash Preview
FrontierMath (Tiers 1-3)65.6%51.2%
FrontierMath Tier 429.3%17.1%
OTIS Mock AIME 2024-202594.7%95.6%
ProofBench77%15%
LMArena Math14671473
MathArena Final-Answer Competitions—67.6%
FrontierMath (Feb 2025 set)—35.6%
FrontierMath Tier 4 (v1)—4.2%

Knowledge Gemini 3 Flash Preview leads

Claude Sonnet 5: 55.6 (#47), Gemini 3 Flash Preview: 58.8 (#33)

BenchmarkClaude Sonnet 5Gemini 3 Flash Preview
GPQA Diamond90.5%89.4%
SimpleQA Verified33.7%66.8%
LMArena Expert14901462
Vectara Hallucination Rate—13.5%

Multimodal Gemini 3 Flash Preview leads

Claude Sonnet 5: 42.4 (#31), Gemini 3 Flash Preview: 45.5 (#16)

BenchmarkClaude Sonnet 5Gemini 3 Flash Preview
LMArena Vision12741285
Blueprint-Bench 224.9%0%
LMArena Document14661413
GeoBench—88%
VPCT—72.6%

Multilingual Gemini 3 Flash Preview leads

Claude Sonnet 5: 53.8 (#55), Gemini 3 Flash Preview: 55.7 (#27)

BenchmarkClaude Sonnet 5Gemini 3 Flash Preview
LMArena Non-English14311458
LMArena Chinese14771511
LMArena French14601477
LMArena German14401497
LMArena Japanese14221489
LMArena Korean14111443
LMArena Russian14511480
LMArena Spanish14371469

Instruction Following Too close to call

Claude Sonnet 5: 76.3 (#41), Gemini 3 Flash Preview: 75.7 (#56)

BenchmarkClaude Sonnet 5Gemini 3 Flash Preview
LMArena Instruction Following14521437

Long Context Too close to call

Claude Sonnet 5: 44.8 (#55), Gemini 3 Flash Preview: 44.4 (#67)

BenchmarkClaude Sonnet 5Gemini 3 Flash Preview
LMArena Longer Query14631452

Writing & Preference Claude Sonnet 5 leads

Claude Sonnet 5: 69.2 (#25), Gemini 3 Flash Preview: 65.5 (#45)

BenchmarkClaude Sonnet 5Gemini 3 Flash Preview
LMArena Text14421466
LMArena Creative Writing14161457
LMArena Multi-Turn14541471
EQ-Bench Creative Writing1794—
EQ-Bench 41236—

Frequently asked questions

Is Claude Sonnet 5 better than Gemini 3 Flash Preview?

Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 52.3 on the Noometry Index. Gemini 3 Flash Preview costs 3.6× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.

Which is cheaper, Claude Sonnet 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 5 lists at $2 and $10.

Is Claude Sonnet 5 or Gemini 3 Flash Preview better for coding?

Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 50.9 in the Noometry coding category.

Which has the bigger context window?

Gemini 3 Flash Preview does, with 1.05M tokens against 1M.

How many benchmarks do Claude Sonnet 5 and Gemini 3 Flash Preview share?

40 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and Gemini 3 Flash Preview has 59.

Related comparisons

Go deeper