Noometry

Model comparison

GPT-4.5 vs GPT-6 Sol

GPT-6 Sol is the stronger model overall, scoring 61.8 to 37.2 on the Noometry Index.

Last verified . 23 shared benchmarks.

GPT-4.5 OpenAI

37.2

Rank #208 Confirmed

GPT-6 Sol OpenAI

61.8

Rank #12 Confirmed

Summary

  • They share 23 benchmarks with published results for both. GPT-4.5 scores higher in 1 category and GPT-6 Sol in 9 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where GPT-6 Sol leads 74.0 to 13.9.
  • The biggest single-benchmark swing is ARC-AGI-2: 0.8% for GPT-4.5 and 89.6% for GPT-6 Sol.

Side by side

GPT-4.5GPT-6 Sol
ProviderOpenAIOpenAI
Noometry Index37.261.8
Released2025-02-272026-09-22
WeightsProprietaryProprietary
Context window—1.05M
Max output—128K
Input $ / M tokens—$2
Output $ / M tokens—$10
Results tracked4245

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

Category by category

Coding GPT-6 Sol leads

GPT-4.5: 42.2 (#109), GPT-6 Sol: 60.1 (#11)

BenchmarkGPT-4.5GPT-6 Sol
LMArena Coding13961447
DeepSWE—68.8%
FrontierCode—49.3%
Aider Polyglot44.9%—
LMArena WebDev—1688
SciCode—57.6%
WeirdML39.4%—
LiveBench Coding75.2%—
ALE-Bench—2,462

Agentic & Tool Use GPT-6 Sol leads

GPT-4.5: 27.9 (#97), GPT-6 Sol: 37.2 (#36)

BenchmarkGPT-4.5GPT-6 Sol
APEX-Agents—54.3%
Cybench17.5%—
GDP.pdf—26.4%
Vending-Bench 2—14,428

Reasoning GPT-6 Sol leads

GPT-4.5: 13.9 (#330), GPT-6 Sol: 74.0 (#9)

BenchmarkGPT-4.5GPT-6 Sol
ARC-AGI-20.8%89.6%
ARC-AGI-110.3%95.5%
LMArena Hard Prompts14031418
Epoch Capabilities Index136.74162.72
SimpleBench34.5%—
NYT Connections (extended)—90.1%
CritPt—30.9%
EnigmaEval3.2%—
EBR-Bench—53.3%
LiveBench Reasoning71.1%—
Mystery Game Puzzles—56%
DTBench—97.3%
LiveBench Data Analysis64.3%—
LMCA—59.1%
ForecastBench61.7—
LiveBench69%—

Math GPT-6 Sol leads

GPT-4.5: 32.6 (#211), GPT-6 Sol: 87.2 (#7)

BenchmarkGPT-4.5GPT-6 Sol
OTIS Mock AIME 2024-202537.8%100%
LMArena Math14121402
FrontierMath (Tiers 1-3)—89.8%
FrontierMath Tier 4—90%
ProofBench—83%
LiveBench Math69.3%—
MATH Level 578.6%—

Knowledge GPT-6 Sol leads

GPT-4.5: 32.5 (#211), GPT-6 Sol: 64.8 (#15)

BenchmarkGPT-4.5GPT-6 Sol
GPQA Diamond68.7%94.3%
LMArena Expert13941439
Humanity's Last Exam5.4%—
SimpleQA Verified—60.7%
Confabulations13.6%—
Vectara Hallucination Rate—6.5%

Multimodal GPT-6 Sol leads

GPT-4.5: 37.6 (#71), GPT-6 Sol: 47.6 (#10)

BenchmarkGPT-4.5GPT-6 Sol
LMArena Vision11951245
VPCT45%—
Blueprint-Bench 2—36.9%
Furniture Assembly—58.3%

Multilingual GPT-4.5 leads

GPT-4.5: 52.5 (#83), GPT-6 Sol: 50.5 (#118)

BenchmarkGPT-4.5GPT-6 Sol
LMArena Non-English14131385
LMArena Chinese14211405
LMArena French14181410
LMArena German14571390
LMArena Japanese14161385
LMArena Korean13921341
LMArena Russian14191401
LMArena Spanish—1384

Instruction Following GPT-6 Sol leads

GPT-4.5: 72.6 (#134), GPT-6 Sol: 74.5 (#94)

BenchmarkGPT-4.5GPT-6 Sol
LMArena Instruction Following14041412
LiveBench Instruction Following72.3%—

Long Context GPT-6 Sol leads

GPT-4.5: 40.4 (#155), GPT-6 Sol: 43.1 (#108)

BenchmarkGPT-4.5GPT-6 Sol
LMArena Longer Query14061411
Fiction.LiveBench63.9%—

Writing & Preference GPT-6 Sol leads

GPT-4.5: 56.9 (#134), GPT-6 Sol: 71.9 (#18)

BenchmarkGPT-4.5GPT-6 Sol
LMArena Text14171395
LMArena Creative Writing13941378
EQ-Bench Creative Writing12582125
LMArena Multi-Turn14441412
Short-Story Creative Writing75.6%—
LiveBench Language61.5%—

Frequently asked questions

Is GPT-4.5 better than GPT-6 Sol?

GPT-6 Sol is the stronger model overall, scoring 61.8 to 37.2 on the Noometry Index.

Is GPT-4.5 or GPT-6 Sol better for coding?

GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 42.2 in the Noometry coding category.

How many benchmarks do GPT-4.5 and GPT-6 Sol share?

23 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and GPT-6 Sol has 45.

Related comparisons

Go deeper