Noometry

Model comparison

Claude Sonnet 4.6 vs GPT-4o

Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 28.6 on the Noometry Index.

Last verified . 34 shared benchmarks.

Claude Sonnet 4.6 Anthropic

50.3

Rank #50 Confirmed

GPT-4o OpenAI

28.6

Rank #324 Confirmed

Summary

  • They share 34 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 10 categories and GPT-4o in 0 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Sonnet 4.6 leads 52.9 to 10.6.
  • The biggest single-benchmark swing is ARC-AGI-1: 86.5% for Claude Sonnet 4.6 and 4.5% for GPT-4o.
  • GPT-4o is cheaper at $2.50 / $10 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.6.
  • Claude Sonnet 4.6 accepts more context: 1M tokens versus 128K.

Side by side

Claude Sonnet 4.6GPT-4o
ProviderAnthropicOpenAI
Noometry Index50.328.6
Released2026-02-172024-05-13
WeightsProprietaryProprietary
Context window1M128K
Max output128K16K
Input $ / M tokens$3$2.50
Output $ / M tokens$15$10
Results tracked5772

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), GPT-4o: 24.8 (#328)

BenchmarkClaude Sonnet 4.6GPT-4o
SWE-bench Verified75.2%31%
WeirdML66.1%25.1%
LMArena Coding15041297
DeepSWE29.9%—
FrontierCode24.3%—
SWE-bench Verified (bash only)—21.6%
Aider Polyglot—45.3%
LMArena WebDev1522—
SciCode46.8%—
GSO—0%
BigCodeBench Instruct—51.1%
LiveBench Coding—51.4%
BigCodeBench Complete—61.1%
CadEval—26%
ALE-Bench1,327—
HumanEval+—87.2%
MBPP+—72.2%

Agentic & Tool Use Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 39.1 (#28), GPT-4o: 21.0 (#141)

BenchmarkClaude Sonnet 4.6GPT-4o
LMArena Search12211006
Terminal-Bench53.4%—
APEX-Agents43%—
OSWorld 2.09.3%—
GDPval—9.9%
TheAgentCompany—8.6%
Cybench—12.5%
DeepResearch Bench54.9%—
OSWorld72.1%—
BALROG—32.3%
ExploitBench23.6%—
GBAEval48.8%—
GDP.pdf18%—
METR Time Horizons—40.8%
Vending-Bench 27,204—

Reasoning Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 46.1 (#45), GPT-4o: 9.4 (#343)

BenchmarkClaude Sonnet 4.6GPT-4o
ARC-AGI-260.4%0%
ARC-AGI-186.5%4.5%
CritPt3.1%0%
Chess Puzzles13%13%
LMArena Hard Prompts14841281
DTBench89.9%64.5%
LMCA46.5%16.6%
Epoch Capabilities Index152.24128.97
ForecastBench6257.7
SimpleBench—17.8%
NYT Connections (extended)80.9%—
EnigmaEval—0.8%
Thematic Generalization76.3%—
LiveBench Reasoning—55.8%
Mystery Game Puzzles16%—
LiveBench Data Analysis—60.9%
LiveBench—55.3%

Math Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 52.9 (#49), GPT-4o: 10.6 (#312)

BenchmarkClaude Sonnet 4.6GPT-4o
OTIS Mock AIME 2024-202585.8%6.4%
LMArena Math14621285
FrontierMath (Feb 2025 set)32.4%0.3%
FrontierMath (Tiers 1-3)—0.4%
ProofBench45%—
Omni-MATH—29.3%
LiveBench Math—49.5%
MATH Level 5—53.3%
FrontierMath Tier 4 (v1)8.3%—

Knowledge Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 51.7 (#65), GPT-4o: 28.8 (#242)

BenchmarkClaude Sonnet 4.6GPT-4o
GPQA Diamond87.4%49.2%
SimpleQA Verified35.5%26%
Vectara Hallucination Rate10.6%9.6%
LMArena Expert15001250
Humanity's Last Exam—2.7%
MMLU-Pro—71.3%
Confabulations—15.3%
GPQA (HELM)—52%
MMLU—88.1%

Multimodal Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 38.0 (#68), GPT-4o: 34.5 (#91)

BenchmarkClaude Sonnet 4.6GPT-4o
LMArena Vision12831137
Video-MME—71.9%
GeoBench—71%
VPCT—40%
Blueprint-Bench 26.7%—
LMArena Document1482—
ScienceQA—88.5%

Multilingual Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 54.4 (#41), GPT-4o: 43.2 (#186)

BenchmarkClaude Sonnet 4.6GPT-4o
LMArena Non-English14401283
LMArena Chinese14911277
LMArena French14651304
LMArena German14281282
LMArena Japanese14201257
LMArena Korean14111234
LMArena Russian14401286
LMArena Spanish14641292

Instruction Following Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 77.4 (#25), GPT-4o: 66.6 (#207)

BenchmarkClaude Sonnet 4.6GPT-4o
LMArena Instruction Following14751278
LiveBench Instruction Following—68.6%
IFEval—81.7%

Long Context Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 45.3 (#44), GPT-4o: 39.4 (#179)

BenchmarkClaude Sonnet 4.6GPT-4o
LMArena Longer Query14791289
Fiction.LiveBench—66.7%

Writing & Preference Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 70.2 (#22), GPT-4o: 52.6 (#166)

BenchmarkClaude Sonnet 4.6GPT-4o
LMArena Text14581300
LMArena Creative Writing14351292
LMArena Multi-Turn14641302
Short-Story Creative Writing—81.8%
EQ-Bench Creative Writing1810—
WildBench—82.8%
EQ-Bench 41207—
LiveBench Language—47.6%

Frequently asked questions

Is Claude Sonnet 4.6 better than GPT-4o?

Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 28.6 on the Noometry Index.

Which is cheaper, Claude Sonnet 4.6 or GPT-4o?

GPT-4o is cheaper. It lists at $2.50 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 GPT-4o better for coding?

Claude Sonnet 4.6 scores higher on coding benchmarks: 46.3 versus 24.8 in the Noometry coding category.

Which has the bigger context window?

Claude Sonnet 4.6 does, with 1M tokens against 128K.

How many benchmarks do Claude Sonnet 4.6 and GPT-4o share?

34 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and GPT-4o has 72.

Related comparisons

Go deeper