Noometry

Model comparison

Claude 3 Opus vs GPT-6 Sol

GPT-6 Sol is the stronger model overall, scoring 61.8 to 29.5 on the Noometry Index.

Last verified . 24 shared benchmarks.

Claude 3 Opus Anthropic

29.5

Rank #310 Confirmed

GPT-6 Sol OpenAI

61.8

Rank #12 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Claude 3 Opus scores higher in 0 categories and GPT-6 Sol in 10 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6 Sol leads 87.2 to 14.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.7% for Claude 3 Opus and 100% for GPT-6 Sol.

Side by side

Claude 3 OpusGPT-6 Sol
ProviderAnthropicOpenAI
Noometry Index29.561.8
Released2024-02-292026-09-22
WeightsProprietaryProprietary
Context window—1.05M
Max output—128K
Input $ / M tokens—$2
Output $ / M tokens—$10
Results tracked4645

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

Category by category

Coding GPT-6 Sol leads

Claude 3 Opus: 32.9 (#267), GPT-6 Sol: 60.1 (#11)

BenchmarkClaude 3 OpusGPT-6 Sol
LMArena Coding12641447
DeepSWE—68.8%
FrontierCode—49.3%
LMArena WebDev—1688
SciCode—57.6%
WeirdML19.2%—
BigCodeBench Instruct45.5%—
LiveBench Coding38.6%—
BigCodeBench Complete57.4%—
ALE-Bench—2,462
HumanEval+77.4%—
MBPP+73.3%—

Agentic & Tool Use GPT-6 Sol leads

Claude 3 Opus: 24.6 (#116), GPT-6 Sol: 37.2 (#36)

BenchmarkClaude 3 OpusGPT-6 Sol
APEX-Agents—54.3%
Cybench10%—
GDP.pdf—26.4%
METR Time Horizons29.5%—
Vending-Bench 2—14,428

Reasoning GPT-6 Sol leads

Claude 3 Opus: 14.6 (#324), GPT-6 Sol: 74.0 (#9)

BenchmarkClaude 3 OpusGPT-6 Sol
LMArena Hard Prompts12451418
DTBench61.6%97.3%
LMCA17%59.1%
Epoch Capabilities Index126.91162.72
ARC-AGI-2—89.6%
SimpleBench23.5%—
NYT Connections (extended)—90.1%
ARC-AGI-1—95.5%
CritPt—30.9%
Chess Puzzles5%—
EnigmaEval0.8%—
EBR-Bench—53.3%
LiveBench Reasoning40.6%—
Mystery Game Puzzles—56%
LiveBench Data Analysis57.9%—
ForecastBench58.4—
LiveBench49.2%—
WinoGrande88.5%—

Math GPT-6 Sol leads

Claude 3 Opus: 14.8 (#299), GPT-6 Sol: 87.2 (#7)

BenchmarkClaude 3 OpusGPT-6 Sol
OTIS Mock AIME 2024-20254.7%100%
LMArena Math12731402
FrontierMath (Tiers 1-3)—89.8%
FrontierMath Tier 4—90%
ProofBench—83%
LiveBench Math43.6%—
MATH Level 537.5%—

Knowledge GPT-6 Sol leads

Claude 3 Opus: 24.5 (#267), GPT-6 Sol: 64.8 (#15)

BenchmarkClaude 3 OpusGPT-6 Sol
GPQA Diamond47.2%94.3%
SimpleQA Verified12.6%60.7%
LMArena Expert12231439
Confabulations22.7%—
Vectara Hallucination Rate—6.5%
MMLU84.6%—

Multimodal GPT-6 Sol leads

Claude 3 Opus: 27.1 (#116), GPT-6 Sol: 47.6 (#10)

BenchmarkClaude 3 OpusGPT-6 Sol
LMArena Vision10231245
Blueprint-Bench 2—36.9%
Furniture Assembly—58.3%

Multilingual GPT-6 Sol leads

Claude 3 Opus: 41.4 (#207), GPT-6 Sol: 50.5 (#118)

BenchmarkClaude 3 OpusGPT-6 Sol
LMArena Non-English12581385
LMArena Chinese12481405
LMArena French12751410
LMArena German12581390
LMArena Japanese12041385
LMArena Korean11871341
LMArena Russian12801401
LMArena Spanish12461384

Instruction Following GPT-6 Sol leads

Claude 3 Opus: 64.1 (#228), GPT-6 Sol: 74.5 (#94)

BenchmarkClaude 3 OpusGPT-6 Sol
LMArena Instruction Following12481412
LiveBench Instruction Following63.9%—

Long Context GPT-6 Sol leads

Claude 3 Opus: 38.2 (#202), GPT-6 Sol: 43.1 (#108)

BenchmarkClaude 3 OpusGPT-6 Sol
LMArena Longer Query12591411

Writing & Preference GPT-6 Sol leads

Claude 3 Opus: 47.2 (#213), GPT-6 Sol: 71.9 (#18)

BenchmarkClaude 3 OpusGPT-6 Sol
LMArena Text12621395
LMArena Creative Writing12351378
LMArena Multi-Turn12751412
EQ-Bench Creative Writing—2125
LiveBench Language50.4%—

Frequently asked questions

Is Claude 3 Opus better than GPT-6 Sol?

GPT-6 Sol is the stronger model overall, scoring 61.8 to 29.5 on the Noometry Index.

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

GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 32.9 in the Noometry coding category.

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

24 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and GPT-6 Sol has 45.

Related comparisons

Go deeper