Noometry

Model comparison

Claude Sonnet 4.6 vs Gemini 2.5 Flash

Claude Sonnet 4.6 is the stronger model overall, scoring 50.1 to 39.0 on the Noometry Index. Gemini 2.5 Flash costs 7.1× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.

Last verified . 34 shared benchmarks.

Claude Sonnet 4.6 Anthropic

50.1

Rank #42 Confirmed

Gemini 2.5 Flash Google

39.0

Rank #162 Confirmed

Summary

  • They share 34 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 8 categories and Gemini 2.5 Flash in 2 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Sonnet 4.6 leads 46.1 to 18.2.
  • The biggest single-benchmark swing is ARC-AGI-2: 60.4% for Claude Sonnet 4.6 and 2.5% 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 4.6.
  • Gemini 2.5 Flash accepts more context: 1.05M tokens versus 1M.

Side by side

Claude Sonnet 4.6Gemini 2.5 Flash
ProviderAnthropicGoogle
Noometry Index50.139.0
Released2026-02-172025-04-17
WeightsProprietaryProprietary
Context window1M1.05M
Max output128K66K
Input $ / M tokens$3$0.30
Output $ / M tokens$15$2.50
Results tracked5754

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

Category by category

Coding Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 46.0 (#62), Gemini 2.5 Flash: 35.5 (#210)

BenchmarkClaude Sonnet 4.6Gemini 2.5 Flash
WeirdML66.1%41.9%
LMArena Coding15041424
ALE-Bench1,327661.88
SWE-bench Verified75.2%—
DeepSWE29.9%—
FrontierCode24.3%—
SWE-bench Verified (bash only)—28.7%
Aider Polyglot—55.1%
LMArena WebDev1521—
SciCode46.8%—

Agentic & Tool Use Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 39.1 (#26), Gemini 2.5 Flash: 30.6 (#67)

BenchmarkClaude Sonnet 4.6Gemini 2.5 Flash
Terminal-Bench53.4%17.1%
Vending-Bench 27,204548.84
APEX-Agents43%—
Berkeley Function Calling Leaderboard—56.2%
OSWorld 2.09.3%—
TheAgentCompany—41.1%
DeepResearch Bench54.9%—
OSWorld72.1%—
BALROG—33.5%
ExploitBench23.6%—
GBAEval48.8%—
GDP.pdf18%—
LMArena Search1221—

Reasoning Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 46.1 (#40), Gemini 2.5 Flash: 18.2 (#271)

BenchmarkClaude Sonnet 4.6Gemini 2.5 Flash
ARC-AGI-260.4%2.5%
ARC-AGI-186.5%33.3%
CritPt3.1%1.1%
LMArena Hard Prompts14851422
DTBench89.9%76.5%
LMCA46.5%27.5%
Epoch Capabilities Index152.25143.04
ForecastBench6260.6
SimpleBench—41.2%
Kagi LLM Benchmark—56.8%
NYT Connections (extended)80.9%—
Chess Puzzles13%—
EnigmaEval—2.7%
Thematic Generalization76.3%—
Mystery Game Puzzles16%—

Math Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 51.9 (#41), Gemini 2.5 Flash: 38.1 (#87)

BenchmarkClaude Sonnet 4.6Gemini 2.5 Flash
OTIS Mock AIME 2024-202585.8%73.1%
LMArena Math14631415
FrontierMath (Feb 2025 set)32.4%4.8%
FrontierMath Tier 4 (v1)8.3%4.2%
ProofBench45%—
Omni-MATH—38.5%

Knowledge Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 51.6 (#60), Gemini 2.5 Flash: 36.1 (#162)

BenchmarkClaude Sonnet 4.6Gemini 2.5 Flash
Vectara Hallucination Rate10.6%7.8%
LMArena Expert15001426
GPQA Diamond87.4%—
Humanity's Last Exam—12.1%
SimpleQA Verified35.5%—
MMLU-Pro—63.9%
Confabulations—16.8%
GPQA (HELM)—39%

Multimodal Gemini 2.5 Flash leads

Claude Sonnet 4.6: 38.0 (#61), Gemini 2.5 Flash: 41.2 (#31)

BenchmarkClaude Sonnet 4.6Gemini 2.5 Flash
LMArena Vision12831254
GeoBench—76%
VPCT—46.2%
Blueprint-Bench 26.7%—
LMArena Document1482—
SpatialViz-Bench—36.9%

Multilingual Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 54.6 (#39), Gemini 2.5 Flash: 52.5 (#83)

BenchmarkClaude Sonnet 4.6Gemini 2.5 Flash
LMArena Non-English14401410
LMArena Chinese14911450
LMArena French14651433
LMArena German14281419
LMArena Japanese14191403
LMArena Korean14111385
LMArena Russian14401415
LMArena Spanish14651421

Instruction Following Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 77.6 (#23), Gemini 2.5 Flash: 75.9 (#50)

BenchmarkClaude Sonnet 4.6Gemini 2.5 Flash
LMArena Instruction Following14761405
IFEval—89.8%

Long Context Gemini 2.5 Flash leads

Claude Sonnet 4.6: 45.3 (#40), Gemini 2.5 Flash: 47.5 (#16)

BenchmarkClaude Sonnet 4.6Gemini 2.5 Flash
LMArena Longer Query14791419
Fiction.LiveBench—77.8%

Writing & Preference Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 70.4 (#22), Gemini 2.5 Flash: 54.0 (#153)

BenchmarkClaude Sonnet 4.6Gemini 2.5 Flash
LMArena Text14581417
LMArena Creative Writing14351400
EQ-Bench Creative Writing18101137
LMArena Multi-Turn14641408
Short-Story Creative Writing—76.5%
WildBench—81.7%
EQ-Bench 41207—

Frequently asked questions

Is Claude Sonnet 4.6 better than Gemini 2.5 Flash?

Claude Sonnet 4.6 is the stronger model overall, scoring 50.1 to 39.0 on the Noometry Index. Gemini 2.5 Flash costs 7.1× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.

Which is cheaper, Claude Sonnet 4.6 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 4.6 lists at $3 and $15.

Is Claude Sonnet 4.6 or Gemini 2.5 Flash better for coding?

Claude Sonnet 4.6 scores higher on coding benchmarks: 46.0 versus 35.5 in the Noometry coding category.

Which has the bigger context window?

Gemini 2.5 Flash does, with 1.05M tokens against 1M.

How many benchmarks do Claude Sonnet 4.6 and Gemini 2.5 Flash share?

34 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Gemini 2.5 Flash has 54.

Related comparisons

Go deeper