Noometry

Model comparison

Claude Sonnet 4.5 vs GPT-5.4 mini

Claude Sonnet 4.5 and GPT-5.4 mini score almost the same on the Noometry Index (44.1 vs 45.0), so choose on price, context window or the category you care about most.

Last verified . 43 shared benchmarks.

Claude Sonnet 4.5 Anthropic

44.1

Rank #81 Confirmed

GPT-5.4 mini OpenAI

45.0

Rank #76 Confirmed

Summary

  • They share 43 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 6 categories and GPT-5.4 mini in 4 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-5.4 mini leads 45.5 to 32.3.
  • The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 23.9% for Claude Sonnet 4.5 and 51.2% for GPT-5.4 mini.
  • GPT-5.4 mini is cheaper at $0.75 / $4.50 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
  • GPT-5.4 mini accepts more context: 400K tokens versus 200K.

Side by side

Claude Sonnet 4.5GPT-5.4 mini
ProviderAnthropicOpenAI
Noometry Index44.145.0
Released2025-09-292026-03-17
WeightsProprietaryProprietary
Context window200K400K
Max output64K128K
Input $ / M tokens$3$0.75
Output $ / M tokens$15$4.50
Results tracked7346

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 mini: 45.2 (#72)

BenchmarkClaude Sonnet 4.5GPT-5.4 mini
LMArena WebDev13931397
SciCode44.7%49.9%
WeirdML47.7%60.3%
LMArena Coding14891438
ALE-Bench796.151,189
SWE-bench Verified71.3%—
FrontierCode—27%
SWE-bench Verified (bash only)71.4%—
SWE-bench Multilingual67%—
GSO14.7%—
AlgoTune1.52—

Agentic & Tool Use Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 38.3 (#32), GPT-5.4 mini: 29.9 (#81)

BenchmarkClaude Sonnet 4.5GPT-5.4 mini
DeepResearch Bench52.6%36.3%
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%—
OSWorld62.9%—
LMArena Search1159—
METR Time Horizons67.4%—
Vending-Bench 23,839—

Reasoning GPT-5.4 mini leads

Claude Sonnet 4.5: 26.9 (#125), GPT-5.4 mini: 30.4 (#85)

BenchmarkClaude Sonnet 4.5GPT-5.4 mini
ARC-AGI-213.6%18.9%
Kagi LLM Benchmark57.9%37.9%
NYT Connections (extended)37.3%61.8%
ARC-AGI-163.7%63.7%
CritPt1.1%10%
Chess Puzzles12%24%
LMArena Hard Prompts14621424
Mystery Game Puzzles17%11%
DTBench83.2%80%
LMCA38.8%40.8%
Epoch Capabilities Index146.84148.84
ForecastBench61.957
SimpleBench54.3%—
EnigmaEval6%—
Thematic Generalization—61.7%
EBR-Bench2.4%—

Math GPT-5.4 mini leads

Claude Sonnet 4.5: 32.3 (#216), GPT-5.4 mini: 45.5 (#75)

BenchmarkClaude Sonnet 4.5GPT-5.4 mini
FrontierMath (Tiers 1-3)23.9%51.2%
FrontierMath Tier 42.4%9.8%
OTIS Mock AIME 2024-202577.8%88.9%
ProofBench19%21%
LMArena Math14491419
FrontierMath (Feb 2025 set)15.2%28.3%
FrontierMath Tier 4 (v1)4.2%2.1%
Omni-MATH55.3%—
MATH Level 597.7%—

Knowledge GPT-5.4 mini leads

Claude Sonnet 4.5: 48.4 (#76), GPT-5.4 mini: 51.5 (#67)

BenchmarkClaude Sonnet 4.5GPT-5.4 mini
GPQA Diamond82.3%86.9%
SimpleQA Verified30.7%29.4%
Vectara Hallucination Rate12%5.5%
LMArena Expert14821435
Humanity's Last Exam13.7%—
MMLU-Pro86.9%—
GPQA (HELM)68.6%—

Multimodal GPT-5.4 mini leads

Claude Sonnet 4.5: 34.8 (#89), GPT-5.4 mini: 39.7 (#56)

BenchmarkClaude Sonnet 4.5GPT-5.4 mini
LMArena Vision—1245
VPCT39.8%—
LMArena Document1450—

Multilingual Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 53.4 (#69), GPT-5.4 mini: 51.9 (#96)

BenchmarkClaude Sonnet 4.5GPT-5.4 mini
LMArena Non-English14251405
LMArena Chinese14591446
LMArena French14581440
LMArena German14271409
LMArena Japanese13901374
LMArena Korean14031368
LMArena Russian14371417
LMArena Spanish14571405

Instruction Following Too close to call

Claude Sonnet 4.5: 75.0 (#78), GPT-5.4 mini: 74.1 (#102)

BenchmarkClaude Sonnet 4.5GPT-5.4 mini
LMArena Instruction Following14591405
IFEval85%—

Long Context Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 45.2 (#46), GPT-5.4 mini: 43.0 (#112)

BenchmarkClaude Sonnet 4.5GPT-5.4 mini
LMArena Longer Query14761407

Writing & Preference Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 66.5 (#34), GPT-5.4 mini: 64.0 (#58)

BenchmarkClaude Sonnet 4.5GPT-5.4 mini
LMArena Text14391412
LMArena Creative Writing14421370
EQ-Bench Creative Writing16781665
LMArena Multi-Turn14651429
WildBench85.4%—

Frequently asked questions

Is Claude Sonnet 4.5 better than GPT-5.4 mini?

Claude Sonnet 4.5 and GPT-5.4 mini score almost the same on the Noometry Index (44.1 vs 45.0), so choose on price, context window or the category you care about most.

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

GPT-5.4 mini is cheaper. It lists at $0.75 per million input tokens and $4.50 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.

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

Claude Sonnet 4.5 scores higher on coding benchmarks: 47.3 versus 45.2 in the Noometry coding category.

Which has the bigger context window?

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

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

43 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and GPT-5.4 mini has 46.

Related comparisons

Go deeper