Noometry

Model comparison

Claude Opus 4.5 vs GPT-4.1 mini

Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 33.6 on the Noometry Index. GPT-4.1 mini costs 14× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.

Last verified . 34 shared benchmarks.

Claude Opus 4.5 Anthropic

50.5

Rank #47 Confirmed

GPT-4.1 mini OpenAI

33.6

Rank #240 Confirmed

Summary

  • They share 34 benchmarks with published results for both. Claude Opus 4.5 scores higher in 9 categories and GPT-4.1 mini in 1 category; 10 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Opus 4.5 leads 42.6 to 10.8.
  • The biggest single-benchmark swing is ARC-AGI-1: 80% for Claude Opus 4.5 and 3.5% for GPT-4.1 mini.
  • GPT-4.1 mini is cheaper at $0.40 / $1.60 per million input/output tokens, against $5 / $25 for Claude Opus 4.5.
  • GPT-4.1 mini accepts more context: 1.05M tokens versus 200K.

Side by side

Claude Opus 4.5GPT-4.1 mini
ProviderAnthropicOpenAI
Noometry Index50.533.6
Released2025-11-012025-04-14
WeightsProprietaryProprietary
Context window200K1.05M
Max output64K33K
Input $ / M tokens$5$0.40
Output $ / M tokens$25$1.60
Results tracked6947

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

Category by category

Coding Claude Opus 4.5 leads

Claude Opus 4.5: 54.8 (#27), GPT-4.1 mini: 30.6 (#293)

BenchmarkClaude Opus 4.5GPT-4.1 mini
SWE-bench Verified (bash only)76.8%23.9%
WeirdML63.7%37.6%
LMArena Coding15041367
SWE-bench Verified76.7%—
Aider Polyglot—32.4%
LMArena WebDev1494—
SWE-bench Multilingual70.7%—
SciCode—40.4%
GSO26.5%—
BigCodeBench Instruct—48.9%
CadEval—16%
ALE-Bench1,025—
AlgoTune1.77—

Agentic & Tool Use Claude Opus 4.5 leads

Claude Opus 4.5: 47.3 (#12), GPT-4.1 mini: 33.3 (#55)

BenchmarkClaude Opus 4.5GPT-4.1 mini
Berkeley Function Calling Leaderboard77.5%50.5%
Terminal-Bench63.1%—
GDPval45.5%—
Remote Labor Index3.8%—
τ²-bench Airline84%—
τ²-bench Banking24.7%—
τ²-bench Retail79.6%—
τ²-bench Telecom92.3%—
Cybench82%—
DeepResearch Bench54.8%—
OSWorld66.3%—
BALROG43.5%—
LMArena Search1180—
METR Time Horizons75%—
Vending-Bench 24,967—

Reasoning Claude Opus 4.5 leads

Claude Opus 4.5: 42.6 (#51), GPT-4.1 mini: 10.8 (#340)

BenchmarkClaude Opus 4.5GPT-4.1 mini
ARC-AGI-237.6%0%
Kagi LLM Benchmark80.2%48.6%
ARC-AGI-180%3.5%
Chess Puzzles12%7%
LMArena Hard Prompts14761349
Mystery Game Puzzles22%7%
DTBench89.9%68.8%
LMCA44.5%21.1%
Epoch Capabilities Index150.09135.01
SimpleBench62%—
NYT Connections (extended)52.5%—
CritPt—0%
EnigmaEval11.9%—
EBR-Bench14.3%—
ForecastBench60.7—

Math Claude Opus 4.5 leads

Claude Opus 4.5: 38.6 (#132), GPT-4.1 mini: 24.1 (#270)

BenchmarkClaude Opus 4.5GPT-4.1 mini
FrontierMath (Tiers 1-3)34.4%6.7%
OTIS Mock AIME 2024-202586.1%44.7%
LMArena Math14631343
FrontierMath (Feb 2025 set)20.7%4.5%
FrontierMath Tier 44.9%—
ProofBench36%—
Omni-MATH—49.1%
MATH Level 5—87.3%
FrontierMath Tier 4 (v1)4.2%—

Knowledge Claude Opus 4.5 leads

Claude Opus 4.5: 56.5 (#44), GPT-4.1 mini: 34.7 (#194)

BenchmarkClaude Opus 4.5GPT-4.1 mini
GPQA Diamond86%65.8%
SimpleQA Verified45.7%12.7%
LMArena Expert14871338
Humanity's Last Exam25.2%—
MMLU-Pro—78.3%
Vectara Hallucination Rate10.9%—
GPQA (HELM)—61.4%

Multimodal GPT-4.1 mini leads

Claude Opus 4.5: 31.4 (#107), GPT-4.1 mini: 35.8 (#82)

BenchmarkClaude Opus 4.5GPT-4.1 mini
LMArena Vision—1181
GeoBench75%—
VPCT40%—
Furniture Assembly28.3%—
LMArena Document1462—

Multilingual Claude Opus 4.5 leads

Claude Opus 4.5: 54.3 (#47), GPT-4.1 mini: 45.7 (#166)

BenchmarkClaude Opus 4.5GPT-4.1 mini
LMArena Non-English14381318
LMArena Chinese14701329
LMArena French14711358
LMArena German14491351
LMArena Japanese14161290
LMArena Korean14241298
LMArena Russian14471324
LMArena Spanish14581319

Instruction Following Claude Opus 4.5 leads

Claude Opus 4.5: 77.5 (#19), GPT-4.1 mini: 73.7 (#118)

BenchmarkClaude Opus 4.5GPT-4.1 mini
LMArena Instruction Following14781333
IFEval—90.4%

Long Context Claude Opus 4.5 leads

Claude Opus 4.5: 46.5 (#22), GPT-4.1 mini: 31.8 (#275)

BenchmarkClaude Opus 4.5GPT-4.1 mini
LMArena Longer Query14801344
Fiction.LiveBench—44.4%
CL-bench21.1%—

Writing & Preference Claude Opus 4.5 leads

Claude Opus 4.5: 68.1 (#28), GPT-4.1 mini: 48.6 (#199)

BenchmarkClaude Opus 4.5GPT-4.1 mini
LMArena Text14511340
LMArena Creative Writing14451300
EQ-Bench Creative Writing16871147
LMArena Multi-Turn14661354
WildBench—83.8%

Frequently asked questions

Is Claude Opus 4.5 better than GPT-4.1 mini?

Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 33.6 on the Noometry Index. GPT-4.1 mini costs 14× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 4.5 or GPT-4.1 mini?

GPT-4.1 mini is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; Claude Opus 4.5 lists at $5 and $25.

Is Claude Opus 4.5 or GPT-4.1 mini better for coding?

Claude Opus 4.5 scores higher on coding benchmarks: 54.8 versus 30.6 in the Noometry coding category.

Which has the bigger context window?

GPT-4.1 mini does, with 1.05M tokens against 200K.

How many benchmarks do Claude Opus 4.5 and GPT-4.1 mini share?

34 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and GPT-4.1 mini has 47.

Related comparisons

Go deeper