Noometry

Model comparison

Claude Sonnet 5 vs GPT-4o

Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 28.6 on the Noometry Index.

Last verified . 32 shared benchmarks.

Claude Sonnet 5 Anthropic

54.6

Rank #29 Confirmed

GPT-4o OpenAI

28.6

Rank #324 Confirmed

Summary

  • They share 32 benchmarks with published results for both. Claude Sonnet 5 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 5 leads 66.2 to 10.6.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 94.7% for Claude Sonnet 5 and 6.4% for GPT-4o.
  • Claude Sonnet 5 is cheaper at $2 / $10 per million input/output tokens, against $2.50 / $10 for GPT-4o.
  • Claude Sonnet 5 accepts more context: 1M tokens versus 128K.

Side by side

Claude Sonnet 5GPT-4o
ProviderAnthropicOpenAI
Noometry Index54.628.6
Released2026-06-292024-05-13
WeightsProprietaryProprietary
Context window1M128K
Max output128K16K
Input $ / M tokens$2$2.50
Output $ / M tokens$10$10
Results tracked5172

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

BenchmarkClaude Sonnet 5GPT-4o
GSO37.3%0%
WeirdML68.8%25.1%
LMArena Coding14831297
SWE-bench Verified—31%
DeepSWE53.8%—
FrontierCode42.7%—
SWE-bench Verified (bash only)—21.6%
Aider Polyglot—45.3%
CursorBench34.1%—
LMArena WebDev1541—
SciCode54.3%—
BigCodeBench Instruct—51.1%
LiveBench Coding—51.4%
BigCodeBench Complete—61.1%
CadEval—26%
ALE-Bench1,463—
HumanEval+—87.2%
MBPP+—72.2%

Agentic & Tool Use Claude Sonnet 5 leads

Claude Sonnet 5: 42.8 (#18), GPT-4o: 21.0 (#141)

BenchmarkClaude Sonnet 5GPT-4o
LMArena Search11941006
APEX-Agents54.5%—
GDPval—9.9%
TheAgentCompany—8.6%
Cybench—12.5%
BALROG—32.3%
GBAEval65.3%—
METR Time Horizons—40.8%
Vending-Bench 26,378—

Reasoning Claude Sonnet 5 leads

Claude Sonnet 5: 49.1 (#39), GPT-4o: 9.4 (#343)

BenchmarkClaude Sonnet 5GPT-4o
SimpleBench60.6%17.8%
CritPt16.9%0%
Chess Puzzles35%13%
LMArena Hard Prompts14611281
DTBench92.5%64.5%
LMCA50%16.6%
Epoch Capabilities Index156.21128.97
ForecastBench61.157.7
ARC-AGI-2—0%
NYT Connections (extended)75.1%—
ARC-AGI-1—4.5%
EnigmaEval—0.8%
LiveBench Reasoning—55.8%
Mystery Game Puzzles35%—
LiveBench Data Analysis—60.9%
Surface Evolver Bench60%—
Bench to the Future 30.14—
LiveBench—55.3%

Math Claude Sonnet 5 leads

Claude Sonnet 5: 66.2 (#27), GPT-4o: 10.6 (#312)

BenchmarkClaude Sonnet 5GPT-4o
FrontierMath (Tiers 1-3)65.6%0.4%
OTIS Mock AIME 2024-202594.7%6.4%
LMArena Math14671285
FrontierMath Tier 429.3%—
ProofBench77%—
Omni-MATH—29.3%
LiveBench Math—49.5%
MATH Level 5—53.3%
FrontierMath (Feb 2025 set)—0.3%

Knowledge Claude Sonnet 5 leads

Claude Sonnet 5: 55.6 (#47), GPT-4o: 28.8 (#242)

BenchmarkClaude Sonnet 5GPT-4o
GPQA Diamond90.5%49.2%
SimpleQA Verified33.7%26%
LMArena Expert14901250
Humanity's Last Exam—2.7%
MMLU-Pro—71.3%
Confabulations—15.3%
Vectara Hallucination Rate—9.6%
GPQA (HELM)—52%
MMLU—88.1%

Multimodal Claude Sonnet 5 leads

Claude Sonnet 5: 42.4 (#31), GPT-4o: 34.5 (#91)

BenchmarkClaude Sonnet 5GPT-4o
LMArena Vision12741137
Video-MME—71.9%
GeoBench—71%
VPCT—40%
Blueprint-Bench 224.9%—
LMArena Document1466—
ScienceQA—88.5%

Multilingual Claude Sonnet 5 leads

Claude Sonnet 5: 53.8 (#55), GPT-4o: 43.2 (#186)

BenchmarkClaude Sonnet 5GPT-4o
LMArena Non-English14311283
LMArena Chinese14771277
LMArena French14601304
LMArena German14401282
LMArena Japanese14221257
LMArena Korean14111234
LMArena Russian14511286
LMArena Spanish14371292

Instruction Following Claude Sonnet 5 leads

Claude Sonnet 5: 76.3 (#41), GPT-4o: 66.6 (#207)

BenchmarkClaude Sonnet 5GPT-4o
LMArena Instruction Following14521278
LiveBench Instruction Following—68.6%
IFEval—81.7%

Long Context Claude Sonnet 5 leads

Claude Sonnet 5: 44.8 (#55), GPT-4o: 39.4 (#179)

BenchmarkClaude Sonnet 5GPT-4o
LMArena Longer Query14631289
Fiction.LiveBench—66.7%

Writing & Preference Claude Sonnet 5 leads

Claude Sonnet 5: 69.2 (#25), GPT-4o: 52.6 (#166)

BenchmarkClaude Sonnet 5GPT-4o
LMArena Text14421300
LMArena Creative Writing14161292
LMArena Multi-Turn14541302
Short-Story Creative Writing—81.8%
EQ-Bench Creative Writing1794—
WildBench—82.8%
EQ-Bench 41236—
LiveBench Language—47.6%

Frequently asked questions

Is Claude Sonnet 5 better than GPT-4o?

Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 28.6 on the Noometry Index.

Which is cheaper, Claude Sonnet 5 or GPT-4o?

Claude Sonnet 5 is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; GPT-4o lists at $2.50 and $10.

Is Claude Sonnet 5 or GPT-4o better for coding?

Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 24.8 in the Noometry coding category.

Which has the bigger context window?

Claude Sonnet 5 does, with 1M tokens against 128K.

How many benchmarks do Claude Sonnet 5 and GPT-4o share?

32 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and GPT-4o has 72.

Related comparisons

Go deeper