Noometry

Model comparison

Claude Sonnet 4.5 vs GPT-4.1

Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 35.9 on the Noometry Index. GPT-4.1 costs 1.7× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

Last verified . 47 shared benchmarks.

Claude Sonnet 4.5 Anthropic

44.1

Rank #81 Confirmed

GPT-4.1 OpenAI

35.9

Rank #219 Confirmed

Summary

  • They share 47 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 9 categories and GPT-4.1 in 1 category; 10 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Sonnet 4.5 leads 26.9 to 11.7.
  • The biggest single-benchmark swing is ARC-AGI-1: 63.7% for Claude Sonnet 4.5 and 5.5% for GPT-4.1.
  • GPT-4.1 is cheaper at $2 / $8 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
  • GPT-4.1 accepts more context: 1.05M tokens versus 200K.

Side by side

Claude Sonnet 4.5GPT-4.1
ProviderAnthropicOpenAI
Noometry Index44.135.9
Released2025-09-292025-04-14
WeightsProprietaryProprietary
Context window200K1.05M
Max output64K33K
Input $ / M tokens$3$2
Output $ / M tokens$15$8
Results tracked7352

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-4.1: 34.4 (#238)

BenchmarkClaude Sonnet 4.5GPT-4.1
SWE-bench Verified71.3%48.5%
SWE-bench Verified (bash only)71.4%39.6%
WeirdML47.7%39%
LMArena Coding14891391
ALE-Bench796.15558.1
Aider Polyglot—52.4%
LMArena WebDev1393—
SWE-bench Multilingual67%—
SciCode44.7%—
GSO14.7%—
CadEval—42%
AlgoTune1.52—

Agentic & Tool Use Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 38.3 (#32), GPT-4.1: 34.7 (#43)

BenchmarkClaude Sonnet 4.5GPT-4.1
Berkeley Function Calling Leaderboard73.2%54%
Terminal-Bench46.5%—
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-4.1: 11.7 (#339)

BenchmarkClaude Sonnet 4.5GPT-4.1
ARC-AGI-213.6%0.4%
SimpleBench54.3%27%
Kagi LLM Benchmark57.9%52.3%
ARC-AGI-163.7%5.5%
Chess Puzzles12%6%
EnigmaEval6%2.2%
LMArena Hard Prompts14621384
DTBench83.2%68.3%
LMCA38.8%25.6%
Epoch Capabilities Index146.84136.78
ForecastBench61.961.5
NYT Connections (extended)37.3%—
CritPt1.1%—
EBR-Bench2.4%—
Mystery Game Puzzles17%—

Math Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 32.3 (#216), GPT-4.1: 22.3 (#280)

BenchmarkClaude Sonnet 4.5GPT-4.1
FrontierMath (Tiers 1-3)23.9%6%
OTIS Mock AIME 2024-202577.8%38.3%
Omni-MATH55.3%47.1%
LMArena Math14491370
MATH Level 597.7%83%
FrontierMath (Feb 2025 set)15.2%5.5%
FrontierMath Tier 4 (v1)4.2%0%
FrontierMath Tier 42.4%—
ProofBench19%—

Knowledge Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 48.4 (#76), GPT-4.1: 37.1 (#160)

BenchmarkClaude Sonnet 4.5GPT-4.1
GPQA Diamond82.3%66.9%
Humanity's Last Exam13.7%5.4%
SimpleQA Verified30.7%31.1%
MMLU-Pro86.9%81.1%
Vectara Hallucination Rate12%5.6%
GPQA (HELM)68.6%65.9%
LMArena Expert14821364

Multimodal GPT-4.1 leads

Claude Sonnet 4.5: 34.8 (#89), GPT-4.1: 38.2 (#67)

BenchmarkClaude Sonnet 4.5GPT-4.1
LMArena Vision—1211
GeoBench—72%
VPCT39.8%—
LMArena Document1450—

Multilingual Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 53.4 (#69), GPT-4.1: 49.4 (#133)

BenchmarkClaude Sonnet 4.5GPT-4.1
LMArena Non-English14251370
LMArena Chinese14591382
LMArena French14581382
LMArena German14271381
LMArena Japanese13901319
LMArena Korean14031339
LMArena Russian14371377
LMArena Spanish14571376

Instruction Following Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 75.0 (#78), GPT-4.1: 71.3 (#153)

BenchmarkClaude Sonnet 4.5GPT-4.1
IFEval85%83.8%
LMArena Instruction Following14591367

Long Context Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 45.2 (#46), GPT-4.1: 40.0 (#163)

BenchmarkClaude Sonnet 4.5GPT-4.1
LMArena Longer Query14761385
Fiction.LiveBench—63.9%

Writing & Preference Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 66.5 (#34), GPT-4.1: 57.6 (#125)

BenchmarkClaude Sonnet 4.5GPT-4.1
LMArena Text14391383
LMArena Creative Writing14421363
EQ-Bench Creative Writing16781420
WildBench85.4%85.4%
LMArena Multi-Turn14651398

Frequently asked questions

Is Claude Sonnet 4.5 better than GPT-4.1?

Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 35.9 on the Noometry Index. GPT-4.1 costs 1.7× 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-4.1?

GPT-4.1 is cheaper. It lists at $2 per million input tokens and $8 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.

Is Claude Sonnet 4.5 or GPT-4.1 better for coding?

Claude Sonnet 4.5 scores higher on coding benchmarks: 47.3 versus 34.4 in the Noometry coding category.

Which has the bigger context window?

GPT-4.1 does, with 1.05M tokens against 200K.

How many benchmarks do Claude Sonnet 4.5 and GPT-4.1 share?

47 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and GPT-4.1 has 52.

Related comparisons

Go deeper