Noometry

Model comparison

Claude Sonnet 4.5 vs GPT-5.6 Sol

GPT-5.6 Sol is the stronger model overall, scoring 65.0 to 44.1 on the Noometry Index.

Last verified . 47 shared benchmarks.

Claude Sonnet 4.5 Anthropic

44.1

Rank #81 Confirmed

GPT-5.6 Sol OpenAI

65.0

Rank #7 Confirmed

Summary

  • They share 47 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 0 categories and GPT-5.6 Sol in 10 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-5.6 Sol leads 85.6 to 32.3.
  • The biggest single-benchmark swing is FrontierMath Tier 4: 2.4% for Claude Sonnet 4.5 and 82.9% for GPT-5.6 Sol.
  • Claude Sonnet 4.5 is cheaper at $3 / $15 per million input/output tokens, against $4 / $20 for GPT-5.6 Sol.
  • GPT-5.6 Sol accepts more context: 1.05M tokens versus 200K.

Side by side

Claude Sonnet 4.5GPT-5.6 Sol
ProviderAnthropicOpenAI
Noometry Index44.165.0
Released2025-09-292026-07-09
WeightsProprietaryProprietary
Context window200K1.05M
Max output64K128K
Input $ / M tokens$3$4
Output $ / M tokens$15$20
Results tracked7365

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

Category by category

Coding GPT-5.6 Sol leads

Claude Sonnet 4.5: 47.3 (#61), GPT-5.6 Sol: 65.1 (#7)

BenchmarkClaude Sonnet 4.5GPT-5.6 Sol
LMArena WebDev13931618
SciCode44.7%57.1%
GSO14.7%76.5%
WeirdML47.7%89.4%
LMArena Coding14891498
ALE-Bench796.152,177
SWE-bench Verified71.3%—
DeepSWE—72.7%
FrontierCode—47.5%
SWE-bench Verified (bash only)71.4%—
CursorBench—41.7%
SWE-bench Multilingual67%—
FrontierSWE—32.2%
MirrorCode—20%
AlgoTune1.52—

Agentic & Tool Use GPT-5.6 Sol leads

Claude Sonnet 4.5: 38.3 (#32), GPT-5.6 Sol: 50.3 (#7)

BenchmarkClaude Sonnet 4.5GPT-5.6 Sol
τ²-bench Banking25.3%46.9%
LMArena Search11591257
Vending-Bench 23,8399,619
Terminal-Bench46.5%—
APEX-Agents—51.4%
Berkeley Function Calling Leaderboard73.2%—
OSWorld 2.0—27.3%
GDPval42.5%—
Remote Labor Index2.1%—
τ²-bench Airline72%—
τ²-bench Retail72.4%—
τ²-bench Telecom84.9%—
Cybench60%—
DeepResearch Bench52.6%—
OSWorld62.9%—
PostTrainBench—36.2%
BALROG—60%
GBAEval—52.6%
GDP.pdf—30.7%
METR Time Horizons67.4%—

Reasoning GPT-5.6 Sol leads

Claude Sonnet 4.5: 26.9 (#125), GPT-5.6 Sol: 74.8 (#8)

BenchmarkClaude Sonnet 4.5GPT-5.6 Sol
ARC-AGI-213.6%92.5%
SimpleBench54.3%71.7%
Kagi LLM Benchmark57.9%67%
NYT Connections (extended)37.3%93.8%
ARC-AGI-163.7%97.5%
CritPt1.1%32.3%
Chess Puzzles12%64%
EnigmaEval6%37.1%
EBR-Bench2.4%44.8%
LMArena Hard Prompts14621484
Mystery Game Puzzles17%58%
DTBench83.2%96%
LMCA38.8%59.2%
Epoch Capabilities Index146.84161.66
Surface Evolver Bench—93.1%
Bench to the Future 3—0.14
ForecastBench61.9—

Math GPT-5.6 Sol leads

Claude Sonnet 4.5: 32.3 (#216), GPT-5.6 Sol: 85.6 (#9)

BenchmarkClaude Sonnet 4.5GPT-5.6 Sol
FrontierMath (Tiers 1-3)23.9%89.1%
FrontierMath Tier 42.4%82.9%
OTIS Mock AIME 2024-202577.8%100%
ProofBench19%83%
LMArena Math14491474
Omni-MATH55.3%—
MATH Level 597.7%—
FrontierMath (Feb 2025 set)15.2%—
FrontierMath Erdős—0%
FrontierMath Tier 4 (v1)4.2%—

Knowledge GPT-5.6 Sol leads

Claude Sonnet 4.5: 48.4 (#76), GPT-5.6 Sol: 64.3 (#18)

BenchmarkClaude Sonnet 4.5GPT-5.6 Sol
GPQA Diamond82.3%93.5%
SimpleQA Verified30.7%69.7%
Vectara Hallucination Rate12%12.4%
LMArena Expert14821516
Humanity's Last Exam13.7%—
MMLU-Pro86.9%—
GPQA (HELM)68.6%—

Multimodal GPT-5.6 Sol leads

Claude Sonnet 4.5: 34.8 (#89), GPT-5.6 Sol: 48.6 (#9)

BenchmarkClaude Sonnet 4.5GPT-5.6 Sol
LMArena Document14501483
LMArena Vision—1281
VPCT39.8%—
Blueprint-Bench 2—33.6%
Furniture Assembly—56.7%

Multilingual GPT-5.6 Sol leads

Claude Sonnet 4.5: 53.4 (#69), GPT-5.6 Sol: 55.3 (#32)

BenchmarkClaude Sonnet 4.5GPT-5.6 Sol
LMArena Non-English14251452
LMArena Chinese14591527
LMArena French14581477
LMArena German14271476
LMArena Japanese13901471
LMArena Korean14031442
LMArena Russian14371468
LMArena Spanish14571441

Instruction Following GPT-5.6 Sol leads

Claude Sonnet 4.5: 75.0 (#78), GPT-5.6 Sol: 77.7 (#16)

BenchmarkClaude Sonnet 4.5GPT-5.6 Sol
LMArena Instruction Following14591482
IFEval85%—

Long Context Too close to call

Claude Sonnet 4.5: 45.2 (#46), GPT-5.6 Sol: 45.4 (#42)

BenchmarkClaude Sonnet 4.5GPT-5.6 Sol
LMArena Longer Query14761480

Writing & Preference GPT-5.6 Sol leads

Claude Sonnet 4.5: 66.5 (#34), GPT-5.6 Sol: 73.3 (#12)

BenchmarkClaude Sonnet 4.5GPT-5.6 Sol
LMArena Text14391457
LMArena Creative Writing14421448
EQ-Bench Creative Writing16781972
LMArena Multi-Turn14651460
WildBench85.4%—
EQ-Bench 4—1250

Frequently asked questions

Is Claude Sonnet 4.5 better than GPT-5.6 Sol?

GPT-5.6 Sol is the stronger model overall, scoring 65.0 to 44.1 on the Noometry Index.

Which is cheaper, Claude Sonnet 4.5 or GPT-5.6 Sol?

Claude Sonnet 4.5 is cheaper. It lists at $3 per million input tokens and $15 per million output tokens; GPT-5.6 Sol lists at $4 and $20.

Is Claude Sonnet 4.5 or GPT-5.6 Sol better for coding?

GPT-5.6 Sol scores higher on coding benchmarks: 65.1 versus 47.3 in the Noometry coding category.

Which has the bigger context window?

GPT-5.6 Sol does, with 1.05M tokens against 200K.

How many benchmarks do Claude Sonnet 4.5 and GPT-5.6 Sol share?

47 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and GPT-5.6 Sol has 65.

Related comparisons

Go deeper