Noometry

Model comparison

Claude Sonnet 4.5 vs GPT-5.5

GPT-5.5 is the stronger model overall, scoring 63.4 to 44.1 on the Noometry Index. Claude Sonnet 4.5 costs 1.9× less per token, which makes it the better buy when GPT-5.5's lead doesn't matter for your workload.

Last verified . 53 shared benchmarks.

Claude Sonnet 4.5 Anthropic

44.1

Rank #81 Confirmed

GPT-5.5 OpenAI

63.4

Rank #9 Confirmed

Summary

  • They share 53 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 0 categories and GPT-5.5 in 10 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-5.5 leads 81.7 to 32.3.
  • The biggest single-benchmark swing is ARC-AGI-2: 13.6% for Claude Sonnet 4.5 and 85% for GPT-5.5.
  • Claude Sonnet 4.5 is cheaper at $3 / $15 per million input/output tokens, against $5 / $30 for GPT-5.5.
  • GPT-5.5 accepts more context: 1.05M tokens versus 200K.

Side by side

Claude Sonnet 4.5GPT-5.5
ProviderAnthropicOpenAI
Noometry Index44.163.4
Released2025-09-292026-04-23
WeightsProprietaryProprietary
Context window200K1.05M
Max output64K128K
Input $ / M tokens$3$5
Output $ / M tokens$15$30
Results tracked7371

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

Category by category

Coding GPT-5.5 leads

Claude Sonnet 4.5: 47.3 (#61), GPT-5.5: 58.2 (#17)

BenchmarkClaude Sonnet 4.5GPT-5.5
SWE-bench Verified71.3%80.6%
LMArena WebDev13931513
SciCode44.7%56.1%
GSO14.7%40.2%
WeirdML47.7%84.9%
LMArena Coding14891494
ALE-Bench796.151,943
DeepSWE—67%
FrontierCode—43%
SWE-bench Verified (bash only)71.4%—
SWE-bench Multilingual67%—
MirrorCode—10%
AlgoTune1.52—

Agentic & Tool Use GPT-5.5 leads

Claude Sonnet 4.5: 38.3 (#32), GPT-5.5: 50.7 (#6)

BenchmarkClaude Sonnet 4.5GPT-5.5
Terminal-Bench46.5%84.7%
Remote Labor Index2.1%6.3%
τ²-bench Banking25.3%44.6%
DeepResearch Bench52.6%54%
LMArena Search11591242
Vending-Bench 23,8397,524
APEX-Agents—55.1%
Berkeley Function Calling Leaderboard73.2%—
OSWorld 2.0—13%
GDPval42.5%—
τ²-bench Airline72%—
τ²-bench Retail72.4%—
τ²-bench Telecom84.9%—
Cybench60%—
OSWorld62.9%—
PostTrainBench—27.2%
ExploitBench—47.4%
GBAEval—53.2%
GDP.pdf—26%
METR Time Horizons67.4%—

Reasoning GPT-5.5 leads

Claude Sonnet 4.5: 26.9 (#125), GPT-5.5: 72.8 (#11)

BenchmarkClaude Sonnet 4.5GPT-5.5
ARC-AGI-213.6%85%
SimpleBench54.3%69%
Kagi LLM Benchmark57.9%88.8%
NYT Connections (extended)37.3%96.2%
ARC-AGI-163.7%95%
CritPt1.1%27.1%
Chess Puzzles12%54%
EBR-Bench2.4%34.3%
LMArena Hard Prompts14621489
Mystery Game Puzzles17%56%
DTBench83.2%96%
LMCA38.8%54.3%
Epoch Capabilities Index146.84159.1
ForecastBench61.960.6
EnigmaEval6%—
Surface Evolver Bench—88.1%
Bench to the Future 3—0.14

Math GPT-5.5 leads

Claude Sonnet 4.5: 32.3 (#216), GPT-5.5: 81.7 (#11)

BenchmarkClaude Sonnet 4.5GPT-5.5
FrontierMath (Tiers 1-3)23.9%85.3%
FrontierMath Tier 42.4%72.5%
OTIS Mock AIME 2024-202577.8%100%
ProofBench19%50%
LMArena Math14491486
FrontierMath (Feb 2025 set)15.2%51.7%
FrontierMath Tier 4 (v1)4.2%35.4%
MathArena Final-Answer Competitions—94.3%
Omni-MATH55.3%—
MATH Level 597.7%—
FrontierMath Erdős—0%

Knowledge GPT-5.5 leads

Claude Sonnet 4.5: 48.4 (#76), GPT-5.5: 64.4 (#17)

BenchmarkClaude Sonnet 4.5GPT-5.5
GPQA Diamond82.3%94%
SimpleQA Verified30.7%63%
Vectara Hallucination Rate12%9.3%
LMArena Expert14821508
Humanity's Last Exam13.7%—
MMLU-Pro86.9%—
GPQA (HELM)68.6%—

Multimodal GPT-5.5 leads

Claude Sonnet 4.5: 34.8 (#89), GPT-5.5: 46.9 (#12)

BenchmarkClaude Sonnet 4.5GPT-5.5
LMArena Document14501486
LMArena Vision—1297
VPCT39.8%—
Blueprint-Bench 2—36.2%
Furniture Assembly—44.2%

Multilingual GPT-5.5 leads

Claude Sonnet 4.5: 53.4 (#69), GPT-5.5: 56.4 (#20)

BenchmarkClaude Sonnet 4.5GPT-5.5
LMArena Non-English14251467
LMArena Chinese14591533
LMArena French14581486
LMArena German14271480
LMArena Japanese13901498
LMArena Korean14031460
LMArena Russian14371473
LMArena Spanish14571468

Instruction Following GPT-5.5 leads

Claude Sonnet 4.5: 75.0 (#78), GPT-5.5: 77.5 (#18)

BenchmarkClaude Sonnet 4.5GPT-5.5
LMArena Instruction Following14591479
IFEval85%—

Long Context GPT-5.5 leads

Claude Sonnet 4.5: 45.2 (#46), GPT-5.5: 48.3 (#12)

BenchmarkClaude Sonnet 4.5GPT-5.5
LMArena Longer Query14761484
CL-bench Life—22.2%

Writing & Preference GPT-5.5 leads

Claude Sonnet 4.5: 66.5 (#34), GPT-5.5: 72.7 (#13)

BenchmarkClaude Sonnet 4.5GPT-5.5
LMArena Text14391472
LMArena Creative Writing14421455
EQ-Bench Creative Writing16781844
LMArena Multi-Turn14651476
WildBench85.4%—
EQ-Bench 4—1315

Frequently asked questions

Is Claude Sonnet 4.5 better than GPT-5.5?

GPT-5.5 is the stronger model overall, scoring 63.4 to 44.1 on the Noometry Index. Claude Sonnet 4.5 costs 1.9× less per token, which makes it the better buy when GPT-5.5's lead doesn't matter for your workload.

Which is cheaper, Claude Sonnet 4.5 or GPT-5.5?

Claude Sonnet 4.5 is cheaper. It lists at $3 per million input tokens and $15 per million output tokens; GPT-5.5 lists at $5 and $30.

Is Claude Sonnet 4.5 or GPT-5.5 better for coding?

GPT-5.5 scores higher on coding benchmarks: 58.2 versus 47.3 in the Noometry coding category.

Which has the bigger context window?

GPT-5.5 does, with 1.05M tokens against 200K.

How many benchmarks do Claude Sonnet 4.5 and GPT-5.5 share?

53 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and GPT-5.5 has 71.

Related comparisons

Go deeper