Noometry

Model comparison

Claude Sonnet 4.5 vs GPT-5.4 nano

Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 41.9 on the Noometry Index. GPT-5.4 nano costs 13× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

Last verified . 39 shared benchmarks.

Claude Sonnet 4.5 Anthropic

44.1

Rank #81 Confirmed

GPT-5.4 nano OpenAI

41.9

Rank #125 Confirmed

Summary

  • They share 39 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 7 categories and GPT-5.4 nano in 2 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Claude Sonnet 4.5 leads 66.5 to 55.7.
  • The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 23.9% for Claude Sonnet 4.5 and 44.9% for GPT-5.4 nano.
  • GPT-5.4 nano is cheaper at $0.20 / $1.25 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
  • GPT-5.4 nano accepts more context: 400K tokens versus 200K.

Side by side

Claude Sonnet 4.5GPT-5.4 nano
ProviderAnthropicOpenAI
Noometry Index44.141.9
Released2025-09-292026-03-17
WeightsProprietaryProprietary
Context window200K400K
Max output64K128K
Input $ / M tokens$3$0.20
Output $ / M tokens$15$1.25
Results tracked7340

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

Category by category

Coding Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 47.3 (#61), GPT-5.4 nano: 43.6 (#84)

BenchmarkClaude Sonnet 4.5GPT-5.4 nano
SciCode44.7%46.9%
WeirdML47.7%49.2%
LMArena Coding14891405
ALE-Bench796.151,005
SWE-bench Verified71.3%—
SWE-bench Verified (bash only)71.4%—
LMArena WebDev1393—
SWE-bench Multilingual67%—
GSO14.7%—
AlgoTune1.52—

Agentic & Tool Use Not comparable

Claude Sonnet 4.5: 38.3 (#32), GPT-5.4 nano: —

BenchmarkClaude Sonnet 4.5GPT-5.4 nano
Terminal-Bench46.5%—
Berkeley Function Calling Leaderboard73.2%—
GDPval42.5%—
Remote Labor Index2.1%—
τ²-bench Airline72%—
τ²-bench Banking25.3%—
τ²-bench Retail72.4%—
τ²-bench Telecom84.9%—
Cybench60%—
DeepResearch Bench52.6%—
OSWorld62.9%—
LMArena Search1159—
METR Time Horizons67.4%—
Vending-Bench 23,839—

Reasoning Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 26.9 (#125), GPT-5.4 nano: 23.7 (#173)

BenchmarkClaude Sonnet 4.5GPT-5.4 nano
ARC-AGI-213.6%5.7%
Kagi LLM Benchmark57.9%39.7%
ARC-AGI-163.7%51.5%
CritPt1.1%9.3%
Chess Puzzles12%30%
LMArena Hard Prompts14621381
Mystery Game Puzzles17%9%
DTBench83.2%80.3%
LMCA38.8%36.9%
Epoch Capabilities Index146.84145.81
ForecastBench61.957.3
SimpleBench54.3%—
NYT Connections (extended)37.3%—
EnigmaEval6%—
EBR-Bench2.4%—

Math GPT-5.4 nano leads

Claude Sonnet 4.5: 32.3 (#216), GPT-5.4 nano: 40.9 (#88)

BenchmarkClaude Sonnet 4.5GPT-5.4 nano
FrontierMath (Tiers 1-3)23.9%44.9%
FrontierMath Tier 42.4%12.2%
OTIS Mock AIME 2024-202577.8%87.8%
ProofBench19%5%
LMArena Math14491406
FrontierMath (Feb 2025 set)15.2%25.9%
FrontierMath Tier 4 (v1)4.2%6.3%
Omni-MATH55.3%—
MATH Level 597.7%—

Knowledge Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 48.4 (#76), GPT-5.4 nano: 41.9 (#103)

BenchmarkClaude Sonnet 4.5GPT-5.4 nano
GPQA Diamond82.3%78.5%
SimpleQA Verified30.7%11.7%
Vectara Hallucination Rate12%3.1%
LMArena Expert14821396
Humanity's Last Exam13.7%—
MMLU-Pro86.9%—
GPQA (HELM)68.6%—

Multimodal GPT-5.4 nano leads

Claude Sonnet 4.5: 34.8 (#89), GPT-5.4 nano: 36.7 (#78)

BenchmarkClaude Sonnet 4.5GPT-5.4 nano
LMArena Vision—1196
VPCT39.8%—
LMArena Document1450—

Multilingual Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 53.4 (#69), GPT-5.4 nano: 48.6 (#140)

BenchmarkClaude Sonnet 4.5GPT-5.4 nano
LMArena Non-English14251359
LMArena Chinese14591392
LMArena French14581396
LMArena German14271367
LMArena Japanese13901343
LMArena Korean14031320
LMArena Russian14371363
LMArena Spanish14571371

Instruction Following Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 75.0 (#78), GPT-5.4 nano: 71.9 (#144)

BenchmarkClaude Sonnet 4.5GPT-5.4 nano
LMArena Instruction Following14591362
IFEval85%—

Long Context Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 45.2 (#46), GPT-5.4 nano: 41.6 (#137)

BenchmarkClaude Sonnet 4.5GPT-5.4 nano
LMArena Longer Query14761366

Writing & Preference Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 66.5 (#34), GPT-5.4 nano: 55.7 (#142)

BenchmarkClaude Sonnet 4.5GPT-5.4 nano
LMArena Text14391372
LMArena Creative Writing14421314
LMArena Multi-Turn14651382
EQ-Bench Creative Writing1678—
WildBench85.4%—

Frequently asked questions

Is Claude Sonnet 4.5 better than GPT-5.4 nano?

Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 41.9 on the Noometry Index. GPT-5.4 nano costs 13× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

Which is cheaper, Claude Sonnet 4.5 or GPT-5.4 nano?

GPT-5.4 nano is cheaper. It lists at $0.20 per million input tokens and $1.25 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.

Is Claude Sonnet 4.5 or GPT-5.4 nano better for coding?

Claude Sonnet 4.5 scores higher on coding benchmarks: 47.3 versus 43.6 in the Noometry coding category.

Which has the bigger context window?

GPT-5.4 nano does, with 400K tokens against 200K.

How many benchmarks do Claude Sonnet 4.5 and GPT-5.4 nano share?

39 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and GPT-5.4 nano has 40.

Related comparisons

Go deeper