Noometry

Model comparison

Claude 3 Sonnet vs GPT-6 Sol

GPT-6 Sol is the stronger model overall, scoring 61.8 to 29.0 on the Noometry Index.

Last verified . 22 shared benchmarks.

Claude 3 Sonnet Anthropic

29.0

Rank #319 Confirmed

GPT-6 Sol OpenAI

61.8

Rank #12 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and GPT-6 Sol in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6 Sol leads 87.2 to 10.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Claude 3 Sonnet and 100% for GPT-6 Sol.

Side by side

Claude 3 SonnetGPT-6 Sol
ProviderAnthropicOpenAI
Noometry Index29.061.8
Released2024-02-292026-09-22
WeightsProprietaryProprietary
Context window—1.05M
Max output—128K
Input $ / M tokens—$2
Output $ / M tokens—$10
Results tracked3045

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

Category by category

Coding GPT-6 Sol leads

Claude 3 Sonnet: 29.6 (#302), GPT-6 Sol: 60.1 (#11)

BenchmarkClaude 3 SonnetGPT-6 Sol
LMArena Coding12231447
DeepSWE—68.8%
FrontierCode—49.3%
LMArena WebDev—1688
SciCode—57.6%
WeirdML10.2%—
BigCodeBench Instruct42.7%—
BigCodeBench Complete53.8%—
ALE-Bench—2,462
HumanEval+64%—
MBPP+69.3%—

Agentic & Tool Use Not comparable

Claude 3 Sonnet: —, GPT-6 Sol: 37.2 (#36)

BenchmarkClaude 3 SonnetGPT-6 Sol
APEX-Agents—54.3%
GDP.pdf—26.4%
Vending-Bench 2—14,428

Reasoning GPT-6 Sol leads

Claude 3 Sonnet: 20.5 (#237), GPT-6 Sol: 74.0 (#9)

BenchmarkClaude 3 SonnetGPT-6 Sol
LMArena Hard Prompts11971418
DTBench53.6%97.3%
Epoch Capabilities Index120.7162.72
ARC-AGI-2—89.6%
NYT Connections (extended)—90.1%
ARC-AGI-1—95.5%
CritPt—30.9%
EBR-Bench—53.3%
Mystery Game Puzzles—56%
LMCA—59.1%
WinoGrande75.1%—

Math GPT-6 Sol leads

Claude 3 Sonnet: 10.7 (#310), GPT-6 Sol: 87.2 (#7)

BenchmarkClaude 3 SonnetGPT-6 Sol
OTIS Mock AIME 2024-20252.5%100%
LMArena Math12131402
FrontierMath (Tiers 1-3)—89.8%
FrontierMath Tier 4—90%
ProofBench—83%
MATH Level 518.2%—

Knowledge GPT-6 Sol leads

Claude 3 Sonnet: 21.1 (#276), GPT-6 Sol: 64.8 (#15)

BenchmarkClaude 3 SonnetGPT-6 Sol
GPQA Diamond40.6%94.3%
LMArena Expert11731439
SimpleQA Verified—60.7%
Vectara Hallucination Rate—6.5%
MMLU75.9%—

Multimodal GPT-6 Sol leads

Claude 3 Sonnet: 25.2 (#125), GPT-6 Sol: 47.6 (#10)

BenchmarkClaude 3 SonnetGPT-6 Sol
LMArena Vision9841245
Blueprint-Bench 2—36.9%
Furniture Assembly—58.3%

Multilingual GPT-6 Sol leads

Claude 3 Sonnet: 37.8 (#234), GPT-6 Sol: 50.5 (#118)

BenchmarkClaude 3 SonnetGPT-6 Sol
LMArena Non-English12051385
LMArena Chinese11891405
LMArena French12291410
LMArena German12041390
LMArena Japanese11311385
LMArena Korean11281341
LMArena Russian12271401
LMArena Spanish12041384

Instruction Following GPT-6 Sol leads

Claude 3 Sonnet: 62.8 (#235), GPT-6 Sol: 74.5 (#94)

BenchmarkClaude 3 SonnetGPT-6 Sol
LMArena Instruction Following11991412

Long Context GPT-6 Sol leads

Claude 3 Sonnet: 36.7 (#228), GPT-6 Sol: 43.1 (#108)

BenchmarkClaude 3 SonnetGPT-6 Sol
LMArena Longer Query12111411

Writing & Preference GPT-6 Sol leads

Claude 3 Sonnet: 42.1 (#238), GPT-6 Sol: 71.9 (#18)

BenchmarkClaude 3 SonnetGPT-6 Sol
LMArena Text12181395
LMArena Creative Writing11861378
LMArena Multi-Turn12271412
EQ-Bench Creative Writing—2125

Frequently asked questions

Is Claude 3 Sonnet better than GPT-6 Sol?

GPT-6 Sol is the stronger model overall, scoring 61.8 to 29.0 on the Noometry Index.

Is Claude 3 Sonnet or GPT-6 Sol better for coding?

GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 29.6 in the Noometry coding category.

How many benchmarks do Claude 3 Sonnet and GPT-6 Sol share?

22 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and GPT-6 Sol has 45.

Related comparisons

Go deeper