Noometry

Model comparison

Claude Opus 4.7 vs GPT-4.1

Claude Opus 4.7 is the stronger model overall, scoring 58.4 to 35.7 on the Noometry Index. GPT-4.1 costs 2.9× less per token, which makes it the better buy when Claude Opus 4.7's lead doesn't matter for your workload.

Last verified . 39 shared benchmarks.

Claude Opus 4.7 Anthropic

58.4

Rank #17 Confirmed

GPT-4.1 OpenAI

35.7

Rank #215 Confirmed

Summary

  • They share 39 benchmarks with published results for both. Claude Opus 4.7 scores higher in 10 categories and GPT-4.1 in 0 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Opus 4.7 leads 66.5 to 21.4.
  • The biggest single-benchmark swing is ARC-AGI-1: 93.5% for Claude Opus 4.7 and 5.5% for GPT-4.1.
  • GPT-4.1 is cheaper at $2 / $8 per million input/output tokens, against $5 / $25 for Claude Opus 4.7.
  • GPT-4.1 accepts more context: 1.05M tokens versus 1M.

Side by side

Claude Opus 4.7GPT-4.1
ProviderAnthropicOpenAI
Noometry Index58.435.7
Released2026-04-142025-04-14
WeightsProprietaryProprietary
Context window1M1.05M
Max output128K33K
Input $ / M tokens$5$2
Output $ / M tokens$25$8
Results tracked6652

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

Category by category

Coding Claude Opus 4.7 leads

Claude Opus 4.7: 59.9 (#10), GPT-4.1: 34.2 (#228)

BenchmarkClaude Opus 4.7GPT-4.1
SWE-bench Verified83.5%48.5%
WeirdML76.4%39%
LMArena Coding15191391
ALE-Bench1,323558.1
FrontierCode38.5%—
SWE-bench Verified (bash only)—39.6%
Aider Polyglot—52.4%
LMArena WebDev1557—
SciCode54.5%—
GSO44.1%—
MirrorCode31.1%—
CadEval—42%

Agentic & Tool Use Claude Opus 4.7 leads

Claude Opus 4.7: 47.9 (#8), GPT-4.1: 34.4 (#40)

BenchmarkClaude Opus 4.7GPT-4.1
Terminal-Bench80.2%—
APEX-Agents49.2%—
Berkeley Function Calling Leaderboard—54%
OSWorld 2.018.2%—
τ²-bench Banking40.2%—
PostTrainBench28.6%—
ExploitBench26.5%—
GBAEval43.8%—
GDP.pdf21%—
LMArena Search1233—
Vending-Bench 210,937—

Reasoning Claude Opus 4.7 leads

Claude Opus 4.7: 53.7 (#24), GPT-4.1: 11.7 (#334)

BenchmarkClaude Opus 4.7GPT-4.1
ARC-AGI-275.8%0.4%
SimpleBench61.7%27%
Kagi LLM Benchmark80.7%52.3%
ARC-AGI-193.5%5.5%
Chess Puzzles30%6%
LMArena Hard Prompts15071384
DTBench94.7%68.3%
LMCA52.2%25.6%
Epoch Capabilities Index156.39136.79
ForecastBench60.361.5
NYT Connections (extended)39%—
CritPt12%—
EnigmaEval—2.2%
Thematic Generalization72.8%—
EBR-Bench19%—
Mystery Game Puzzles28%—

Math Claude Opus 4.7 leads

Claude Opus 4.7: 66.5 (#20), GPT-4.1: 21.4 (#269)

BenchmarkClaude Opus 4.7GPT-4.1
FrontierMath (Tiers 1-3)70.2%6%
OTIS Mock AIME 2024-202597.8%38.3%
LMArena Math14991369
FrontierMath (Feb 2025 set)43.8%5.5%
FrontierMath Tier 4 (v1)22.9%0%
FrontierMath Tier 431.7%—
MathArena Final-Answer Competitions73.6%—
ProofBench54%—
Omni-MATH—47.1%
MATH Level 5—83%

Knowledge Claude Opus 4.7 leads

Claude Opus 4.7: 62.6 (#20), GPT-4.1: 37.0 (#152)

BenchmarkClaude Opus 4.7GPT-4.1
GPQA Diamond90.2%66.9%
Humanity's Last Exam36.2%5.4%
SimpleQA Verified51.7%31.1%
Vectara Hallucination Rate12%5.6%
LMArena Expert15211364
MMLU-Pro—81.1%
GPQA (HELM)—65.9%

Multimodal Claude Opus 4.7 leads

Claude Opus 4.7: 41.5 (#29), GPT-4.1: 37.5 (#66)

BenchmarkClaude Opus 4.7GPT-4.1
LMArena Vision13171210
GeoBench—72%
Blueprint-Bench 224.5%—
Furniture Assembly33.3%—
LMArena Document1495—

Multilingual Claude Opus 4.7 leads

Claude Opus 4.7: 57.5 (#9), GPT-4.1: 49.6 (#128)

BenchmarkClaude Opus 4.7GPT-4.1
LMArena Non-English14811370
LMArena Chinese15301382
LMArena French15051383
LMArena German14941380
LMArena Japanese14721320
LMArena Korean14661339
LMArena Russian14941377
LMArena Spanish14971375

Instruction Following Claude Opus 4.7 leads

Claude Opus 4.7: 78.6 (#9), GPT-4.1: 71.5 (#148)

BenchmarkClaude Opus 4.7GPT-4.1
LMArena Instruction Following14981367
IFEval—83.8%

Long Context Claude Opus 4.7 leads

Claude Opus 4.7: 46.1 (#24), GPT-4.1: 40.0 (#158)

BenchmarkClaude Opus 4.7GPT-4.1
LMArena Longer Query15051385
Fiction.LiveBench—63.9%

Writing & Preference Claude Opus 4.7 leads

Claude Opus 4.7: 75.3 (#8), GPT-4.1: 57.8 (#120)

BenchmarkClaude Opus 4.7GPT-4.1
LMArena Text14911383
LMArena Creative Writing14861363
EQ-Bench Creative Writing19141420
LMArena Multi-Turn15061398
WildBench—85.4%
EQ-Bench 41311—

Frequently asked questions

Is Claude Opus 4.7 better than GPT-4.1?

Claude Opus 4.7 is the stronger model overall, scoring 58.4 to 35.7 on the Noometry Index. GPT-4.1 costs 2.9× less per token, which makes it the better buy when Claude Opus 4.7's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 4.7 or GPT-4.1?

GPT-4.1 is cheaper. It lists at $2 per million input tokens and $8 per million output tokens; Claude Opus 4.7 lists at $5 and $25.

Is Claude Opus 4.7 or GPT-4.1 better for coding?

Claude Opus 4.7 scores higher on coding benchmarks: 59.9 versus 34.2 in the Noometry coding category.

Which has the bigger context window?

GPT-4.1 does, with 1.05M tokens against 1M.

How many benchmarks do Claude Opus 4.7 and GPT-4.1 share?

39 benchmarks have published results for both models. Claude Opus 4.7 has 66 scored results on Noometry and GPT-4.1 has 52.

Related comparisons

Go deeper