Noometry

Model comparison

Claude Sonnet 4.6 vs Gemini 2.5 Pro

Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 45.0 on the Noometry Index. Gemini 2.5 Pro costs 1.7× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.

Last verified . 42 shared benchmarks.

Claude Sonnet 4.6 Anthropic

50.3

Rank #50 Confirmed

Gemini 2.5 Pro Google

45.0

Rank #75 Confirmed

Summary

  • They share 42 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 6 categories and Gemini 2.5 Pro in 4 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Sonnet 4.6 leads 52.9 to 32.5.
  • The biggest single-benchmark swing is ARC-AGI-2: 60.4% for Claude Sonnet 4.6 and 4.9% for Gemini 2.5 Pro.
  • Gemini 2.5 Pro is cheaper at $1.25 / $10 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.6.
  • Gemini 2.5 Pro accepts more context: 1.05M tokens versus 1M.

Side by side

Claude Sonnet 4.6Gemini 2.5 Pro
ProviderAnthropicGoogle
Noometry Index50.345.0
Released2026-02-172025-03-25
WeightsProprietaryProprietary
Context window1M1.05M
Max output128K66K
Input $ / M tokens$3$1.25
Output $ / M tokens$15$10
Results tracked5778

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: 46.3 (#67), Gemini 2.5 Pro: 42.4 (#101)

BenchmarkClaude Sonnet 4.6Gemini 2.5 Pro
SWE-bench Verified75.2%57.6%
LMArena WebDev15221227
SciCode46.8%42.8%
WeirdML66.1%54%
LMArena Coding15041452
ALE-Bench1,327785.52
DeepSWE29.9%—
FrontierCode24.3%—
SWE-bench Verified (bash only)—53.6%
Aider Polyglot—83.1%
GSO—3.9%
LiveBench Coding—85.9%
CadEval—64%
AlgoTune—1.51

Agentic & Tool Use Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 39.1 (#28), Gemini 2.5 Pro: 29.2 (#88)

BenchmarkClaude Sonnet 4.6Gemini 2.5 Pro
Terminal-Bench53.4%32.6%
DeepResearch Bench54.9%42.8%
LMArena Search12211142
Vending-Bench 27,204573.64
APEX-Agents43%—
OSWorld 2.09.3%—
GDPval—23.3%
Remote Labor Index—0.8%
TheAgentCompany—30.3%
τ²-bench Banking—13.7%
OSWorld72.1%—
BALROG—43.3%
ExploitBench23.6%—
GBAEval48.8%—
GDP.pdf18%—
METR Time Horizons—55.4%

Reasoning Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 46.1 (#45), Gemini 2.5 Pro: 28.8 (#99)

BenchmarkClaude Sonnet 4.6Gemini 2.5 Pro
ARC-AGI-260.4%4.9%
ARC-AGI-186.5%41%
CritPt3.1%2%
Chess Puzzles13%20%
LMArena Hard Prompts14841455
DTBench89.9%82.4%
LMCA46.5%34.8%
Epoch Capabilities Index152.24145.32
ForecastBench6261.3
SimpleBench—62.4%
Kagi LLM Benchmark—70.3%
NYT Connections (extended)80.9%—
EnigmaEval—5.6%
Thematic Generalization76.3%—
LiveBench Reasoning—89.8%
Mystery Game Puzzles16%—
LiveBench Data Analysis—79.9%
LiveBench—82.3%

Math Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 52.9 (#49), Gemini 2.5 Pro: 32.5 (#213)

BenchmarkClaude Sonnet 4.6Gemini 2.5 Pro
OTIS Mock AIME 2024-202585.8%84.7%
LMArena Math14621450
FrontierMath (Feb 2025 set)32.4%14.1%
FrontierMath Tier 4 (v1)8.3%4.2%
FrontierMath (Tiers 1-3)—24.6%
FrontierMath Tier 4—0%
ProofBench45%—
Omni-MATH—41.6%
LiveBench Math—90.2%
MATH Level 5—95.9%

Knowledge Gemini 2.5 Pro leads

Claude Sonnet 4.6: 51.7 (#65), Gemini 2.5 Pro: 56.0 (#46)

BenchmarkClaude Sonnet 4.6Gemini 2.5 Pro
GPQA Diamond87.4%85.3%
Vectara Hallucination Rate10.6%7%
LMArena Expert15001452
Humanity's Last Exam—21.6%
SimpleQA Verified35.5%—
MMLU-Pro—86.3%
Confabulations—10.6%
GPQA (HELM)—74.9%

Multimodal Gemini 2.5 Pro leads

Claude Sonnet 4.6: 38.0 (#68), Gemini 2.5 Pro: 45.2 (#18)

BenchmarkClaude Sonnet 4.6Gemini 2.5 Pro
LMArena Vision12831263
LMArena Document14821421
GeoBench—86%
VPCT—48%
Blueprint-Bench 26.7%—
SpatialViz-Bench—44.7%

Multilingual Too close to call

Claude Sonnet 4.6: 54.4 (#41), Gemini 2.5 Pro: 55.3 (#31)

BenchmarkClaude Sonnet 4.6Gemini 2.5 Pro
LMArena Non-English14401451
LMArena Chinese14911507
LMArena French14651472
LMArena German14281487
LMArena Japanese14201461
LMArena Korean14111434
LMArena Russian14401461
LMArena Spanish14641473

Instruction Following Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 77.4 (#25), Gemini 2.5 Pro: 75.0 (#75)

BenchmarkClaude Sonnet 4.6Gemini 2.5 Pro
LMArena Instruction Following14751437
LiveBench Instruction Following—80.6%
IFEval—84%

Long Context Gemini 2.5 Pro leads

Claude Sonnet 4.6: 45.3 (#44), Gemini 2.5 Pro: 59.8 (#5)

BenchmarkClaude Sonnet 4.6Gemini 2.5 Pro
LMArena Longer Query14791449
Fiction.LiveBench—91.7%

Writing & Preference Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 70.2 (#22), Gemini 2.5 Pro: 63.7 (#62)

BenchmarkClaude Sonnet 4.6Gemini 2.5 Pro
LMArena Text14581458
LMArena Creative Writing14351454
EQ-Bench Creative Writing18101421
LMArena Multi-Turn14641453
Short-Story Creative Writing—83.8%
WildBench—85.7%
EQ-Bench 41207—
LiveBench Language—67.8%

Frequently asked questions

Is Claude Sonnet 4.6 better than Gemini 2.5 Pro?

Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 45.0 on the Noometry Index. Gemini 2.5 Pro costs 1.7× 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 Pro?

Gemini 2.5 Pro is cheaper. It lists at $1.25 per million input tokens and $10 per million output tokens; Claude Sonnet 4.6 lists at $3 and $15.

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

Claude Sonnet 4.6 scores higher on coding benchmarks: 46.3 versus 42.4 in the Noometry coding category.

Which has the bigger context window?

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

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

42 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Gemini 2.5 Pro has 78.

Related comparisons

Go deeper