Noometry

Model comparison

Claude 3 Sonnet vs GPT-4.1

GPT-4.1 is the stronger model overall, scoring 35.9 to 29.0 on the Noometry Index.

Last verified . 24 shared benchmarks.

Claude 3 Sonnet Anthropic

29.0

Rank #319 Confirmed

GPT-4.1 OpenAI

35.9

Rank #219 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Claude 3 Sonnet scores higher in 1 category and GPT-4.1 in 8 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GPT-4.1 leads 37.1 to 21.1.
  • The biggest single-benchmark swing is MATH Level 5: 18.2% for Claude 3 Sonnet and 83% for GPT-4.1.

Side by side

Claude 3 SonnetGPT-4.1
ProviderAnthropicOpenAI
Noometry Index29.035.9
Released2024-02-292025-04-14
WeightsProprietaryProprietary
Context window—1.05M
Max output—33K
Input $ / M tokens—$2
Output $ / M tokens—$8
Results tracked3052

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

Category by category

Coding GPT-4.1 leads

Claude 3 Sonnet: 29.6 (#302), GPT-4.1: 34.4 (#238)

BenchmarkClaude 3 SonnetGPT-4.1
WeirdML10.2%39%
LMArena Coding12231391
SWE-bench Verified—48.5%
SWE-bench Verified (bash only)—39.6%
Aider Polyglot—52.4%
BigCodeBench Instruct42.7%—
BigCodeBench Complete53.8%—
CadEval—42%
ALE-Bench—558.1
HumanEval+64%—
MBPP+69.3%—

Agentic & Tool Use Not comparable

Claude 3 Sonnet: —, GPT-4.1: 34.7 (#43)

BenchmarkClaude 3 SonnetGPT-4.1
Berkeley Function Calling Leaderboard—54%

Reasoning Claude 3 Sonnet leads

Claude 3 Sonnet: 20.5 (#237), GPT-4.1: 11.7 (#339)

BenchmarkClaude 3 SonnetGPT-4.1
LMArena Hard Prompts11971384
DTBench53.6%68.3%
Epoch Capabilities Index120.7136.78
ARC-AGI-2—0.4%
SimpleBench—27%
Kagi LLM Benchmark—52.3%
ARC-AGI-1—5.5%
Chess Puzzles—6%
EnigmaEval—2.2%
LMCA—25.6%
ForecastBench—61.5
WinoGrande75.1%—

Math GPT-4.1 leads

Claude 3 Sonnet: 10.7 (#310), GPT-4.1: 22.3 (#280)

BenchmarkClaude 3 SonnetGPT-4.1
OTIS Mock AIME 2024-20252.5%38.3%
LMArena Math12131370
MATH Level 518.2%83%
FrontierMath (Tiers 1-3)—6%
Omni-MATH—47.1%
FrontierMath (Feb 2025 set)—5.5%
FrontierMath Tier 4 (v1)—0%

Knowledge GPT-4.1 leads

Claude 3 Sonnet: 21.1 (#276), GPT-4.1: 37.1 (#160)

BenchmarkClaude 3 SonnetGPT-4.1
GPQA Diamond40.6%66.9%
LMArena Expert11731364
Humanity's Last Exam—5.4%
SimpleQA Verified—31.1%
MMLU-Pro—81.1%
Vectara Hallucination Rate—5.6%
GPQA (HELM)—65.9%
MMLU75.9%—

Multimodal GPT-4.1 leads

Claude 3 Sonnet: 25.2 (#125), GPT-4.1: 38.2 (#67)

BenchmarkClaude 3 SonnetGPT-4.1
LMArena Vision9841211
GeoBench—72%

Multilingual GPT-4.1 leads

Claude 3 Sonnet: 37.8 (#234), GPT-4.1: 49.4 (#133)

BenchmarkClaude 3 SonnetGPT-4.1
LMArena Non-English12051370
LMArena Chinese11891382
LMArena French12291382
LMArena German12041381
LMArena Japanese11311319
LMArena Korean11281339
LMArena Russian12271377
LMArena Spanish12041376

Instruction Following GPT-4.1 leads

Claude 3 Sonnet: 62.8 (#235), GPT-4.1: 71.3 (#153)

BenchmarkClaude 3 SonnetGPT-4.1
LMArena Instruction Following11991367
IFEval—83.8%

Long Context GPT-4.1 leads

Claude 3 Sonnet: 36.7 (#228), GPT-4.1: 40.0 (#163)

BenchmarkClaude 3 SonnetGPT-4.1
LMArena Longer Query12111385
Fiction.LiveBench—63.9%

Writing & Preference GPT-4.1 leads

Claude 3 Sonnet: 42.1 (#238), GPT-4.1: 57.6 (#125)

BenchmarkClaude 3 SonnetGPT-4.1
LMArena Text12181383
LMArena Creative Writing11861363
LMArena Multi-Turn12271398
EQ-Bench Creative Writing—1420
WildBench—85.4%

Frequently asked questions

Is Claude 3 Sonnet better than GPT-4.1?

GPT-4.1 is the stronger model overall, scoring 35.9 to 29.0 on the Noometry Index.

Is Claude 3 Sonnet or GPT-4.1 better for coding?

GPT-4.1 scores higher on coding benchmarks: 34.4 versus 29.6 in the Noometry coding category.

How many benchmarks do Claude 3 Sonnet and GPT-4.1 share?

24 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and GPT-4.1 has 52.

Related comparisons

Go deeper