Noometry

Model comparison

Claude Sonnet 4.5 vs GPT-4o mini

Claude Sonnet 4.5 is the stronger model overall, scoring 44.0 to 25.4 on the Noometry Index. GPT-4o mini costs 23× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

Last verified . 38 shared benchmarks.

Claude Sonnet 4.5 Anthropic

44.0

Rank #76 Confirmed

GPT-4o mini OpenAI

25.4

Rank #337 Confirmed

Summary

  • They share 38 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 10 categories and GPT-4o mini in 0 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Claude Sonnet 4.5 leads 48.4 to 17.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 77.8% for Claude Sonnet 4.5 and 6.9% for GPT-4o mini.
  • GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
  • Claude Sonnet 4.5 accepts more context: 1M tokens versus 128K.

Side by side

Claude Sonnet 4.5GPT-4o mini
ProviderAnthropicOpenAI
Noometry Index44.025.4
Released2025-09-292024-07-18
WeightsProprietaryProprietary
Context window1M128K
Max output64K16K
Input $ / M tokens$3$0.15
Output $ / M tokens$15$0.60
Results tracked7360

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

Category by category

Coding Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 47.8 (#54), GPT-4o mini: 21.6 (#330)

BenchmarkClaude Sonnet 4.5GPT-4o mini
WeirdML47.7%11.8%
LMArena Coding14891290
SWE-bench Verified71.3%—
SWE-bench Verified (bash only)71.4%—
Aider Polyglot—3.6%
LMArena WebDev1393—
SWE-bench Multilingual67%—
SciCode44.7%—
GSO14.7%—
BigCodeBench Instruct—46.1%
LiveBench Coding—43.1%
BigCodeBench Complete—57.4%
ALE-Bench796.15—
AlgoTune1.52—
HumanEval+—83.5%
MBPP+—72.2%

Agentic & Tool Use Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 38.1 (#30), GPT-4o mini: 27.2 (#95)

BenchmarkClaude Sonnet 4.5GPT-4o mini
Terminal-Bench46.5%—
Berkeley Function Calling Leaderboard73.2%—
GDPval42.5%—
Remote Labor Index2.1%—
τ²-bench Airline72%—
τ²-bench Banking25.3%—
τ²-bench Retail72.4%—
τ²-bench Telecom84.9%—
Cybench60%—
DeepResearch Bench52.6%—
OSWorld62.9%—
BALROG—17.4%
LMArena Search1159—
METR Time Horizons67.4%—
Vending-Bench 23,839—

Reasoning Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 26.9 (#113), GPT-4o mini: 8.7 (#343)

BenchmarkClaude Sonnet 4.5GPT-4o mini
ARC-AGI-213.6%0%
SimpleBench54.3%10.7%
Kagi LLM Benchmark57.9%28.8%
Chess Puzzles12%0%
LMArena Hard Prompts14621267
Mystery Game Puzzles17%12%
DTBench83.2%54.4%
LMCA38.8%10.4%
Epoch Capabilities Index146.84126.56
NYT Connections (extended)37.3%—
ARC-AGI-163.7%—
CritPt1.1%—
EnigmaEval6%—
EBR-Bench2.4%—
LiveBench Reasoning—32.8%
LiveBench Data Analysis—50%
ForecastBench61.9—
LiveBench—41.3%
PIQA—88.7%

Math Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 31.9 (#190), GPT-4o mini: 9.9 (#307)

BenchmarkClaude Sonnet 4.5GPT-4o mini
FrontierMath (Tiers 1-3)23.9%0.7%
OTIS Mock AIME 2024-202577.8%6.9%
Omni-MATH55.3%28%
LMArena Math14481267
MATH Level 597.7%52.6%
FrontierMath Tier 42.4%—
ProofBench19%—
LiveBench Math—36.3%
FrontierMath (Feb 2025 set)15.2%—
FrontierMath Tier 4 (v1)4.2%—
GSM8K—91.3%

Knowledge Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 48.4 (#70), GPT-4o mini: 17.7 (#279)

BenchmarkClaude Sonnet 4.5GPT-4o mini
GPQA Diamond82.3%37.7%
SimpleQA Verified30.7%8.3%
MMLU-Pro86.9%60.3%
GPQA (HELM)68.6%36.8%
LMArena Expert14831235
Humanity's Last Exam13.7%—
Confabulations—37.2%
Vectara Hallucination Rate12%—
BoolQ—88.7%
MMLU—81.8%

Multimodal Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 34.1 (#84), GPT-4o mini: 25.3 (#117)

BenchmarkClaude Sonnet 4.5GPT-4o mini
VPCT39.8%34%
LMArena Vision—1066
Video-MME—64.8%
GeoBench—64%
LMArena Document1450—

Multilingual Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 53.6 (#65), GPT-4o mini: 42.2 (#194)

BenchmarkClaude Sonnet 4.5GPT-4o mini
LMArena Non-English14251266
LMArena Chinese14591264
LMArena French14591296
LMArena German14271272
LMArena Japanese13901216
LMArena Korean14031195
LMArena Russian14361275
LMArena Spanish14571276

Instruction Following Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 75.2 (#74), GPT-4o mini: 62.1 (#234)

BenchmarkClaude Sonnet 4.5GPT-4o mini
IFEval85%78.2%
LMArena Instruction Following14591259
LiveBench Instruction Following—56.8%

Long Context Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 45.2 (#45), GPT-4o mini: 39.1 (#181)

BenchmarkClaude Sonnet 4.5GPT-4o mini
LMArena Longer Query14761289

Writing & Preference Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 66.7 (#33), GPT-4o mini: 39.7 (#243)

BenchmarkClaude Sonnet 4.5GPT-4o mini
LMArena Text14391286
LMArena Creative Writing14421268
EQ-Bench Creative Writing1678873
WildBench85.4%79.1%
LMArena Multi-Turn14651285
Short-Story Creative Writing—67.2%
LiveBench Language—28.6%

Frequently asked questions

Is Claude Sonnet 4.5 better than GPT-4o mini?

Claude Sonnet 4.5 is the stronger model overall, scoring 44.0 to 25.4 on the Noometry Index. GPT-4o mini costs 23× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

Which is cheaper, Claude Sonnet 4.5 or GPT-4o mini?

GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.

Is Claude Sonnet 4.5 or GPT-4o mini better for coding?

Claude Sonnet 4.5 scores higher on coding benchmarks: 47.8 versus 21.6 in the Noometry coding category.

Which has the bigger context window?

Claude Sonnet 4.5 does, with 1M tokens against 128K.

How many benchmarks do Claude Sonnet 4.5 and GPT-4o mini share?

38 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and GPT-4o mini has 60.

Related comparisons

Go deeper