Noometry

Model comparison

Claude Sonnet 4.5 vs Phi-4

Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 31.2 on the Noometry Index. Phi-4 costs 69× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

Last verified . 24 shared benchmarks.

Claude Sonnet 4.5 Anthropic

44.1

Rank #81 Confirmed

Phi-4 Microsoft

31.2

Rank #279 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 9 categories and Phi-4 in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Claude Sonnet 4.5 leads 66.5 to 40.5.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 77.8% for Claude Sonnet 4.5 and 13.8% for Phi-4.
  • Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
  • Claude Sonnet 4.5 accepts more context: 200K tokens versus 128K.
  • Phi-4 has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 4.5Phi-4
ProviderAnthropicMicrosoft
Noometry Index44.131.2
Released2025-09-292024-12-11
WeightsProprietaryOpen
Context window200K128K
Max output64K4K
Input $ / M tokens$3$0.07
Output $ / M tokens$15$0.14
Results tracked7337

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: 47.3 (#61), Phi-4: 34.4 (#239)

BenchmarkClaude Sonnet 4.5Phi-4
LMArena Coding14891231
SWE-bench Verified71.3%—
SWE-bench Verified (bash only)71.4%—
LMArena WebDev1393—
SWE-bench Multilingual67%—
SciCode44.7%—
GSO14.7%—
WeirdML47.7%—
BigCodeBench Instruct—45.5%
LiveBench Coding—30.7%
BigCodeBench Complete—55.4%
ALE-Bench796.15—
AlgoTune1.52—

Agentic & Tool Use Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 38.3 (#32), Phi-4: 22.8 (#128)

BenchmarkClaude Sonnet 4.5Phi-4
Berkeley Function Calling Leaderboard73.2%28.8%
Terminal-Bench46.5%—
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—11.6%
LMArena Search1159—
METR Time Horizons67.4%—
Vending-Bench 23,839—

Reasoning Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 26.9 (#125), Phi-4: 17.7 (#291)

BenchmarkClaude Sonnet 4.5Phi-4
Chess Puzzles12%1%
LMArena Hard Prompts14621220
Epoch Capabilities Index146.84130.42
ARC-AGI-213.6%—
SimpleBench54.3%—
Kagi LLM Benchmark57.9%—
NYT Connections (extended)37.3%—
ARC-AGI-163.7%—
CritPt1.1%—
EnigmaEval6%—
EBR-Bench2.4%—
LiveBench Reasoning—47.8%
Mystery Game Puzzles17%—
DTBench83.2%—
LiveBench Data Analysis—45.2%
LMCA38.8%—
ForecastBench61.9—
LiveBench—41.6%

Math Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 32.3 (#216), Phi-4: 20.8 (#285)

BenchmarkClaude Sonnet 4.5Phi-4
OTIS Mock AIME 2024-202577.8%13.8%
LMArena Math14491246
MATH Level 597.7%64.9%
FrontierMath (Tiers 1-3)23.9%—
FrontierMath Tier 42.4%—
ProofBench19%—
Omni-MATH55.3%—
LiveBench Math—42%
FrontierMath (Feb 2025 set)15.2%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 48.4 (#76), Phi-4: 32.6 (#209)

BenchmarkClaude Sonnet 4.5Phi-4
GPQA Diamond82.3%56.1%
Vectara Hallucination Rate12%3.7%
LMArena Expert14821203
Humanity's Last Exam13.7%—
SimpleQA Verified30.7%—
MMLU-Pro86.9%—
Confabulations—29.4%
GPQA (HELM)68.6%—
MMLU—84.8%

Multimodal Not comparable

Claude Sonnet 4.5: 34.8 (#89), Phi-4: —

BenchmarkClaude Sonnet 4.5Phi-4
VPCT39.8%—
LMArena Document1450—

Multilingual Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 53.4 (#69), Phi-4: 37.2 (#237)

BenchmarkClaude Sonnet 4.5Phi-4
LMArena Non-English14251197
LMArena Chinese14591212
LMArena French14581224
LMArena German14271222
LMArena Japanese13901158
LMArena Korean14031151
LMArena Russian14371209
LMArena Spanish14571234

Instruction Following Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 75.0 (#78), Phi-4: 60.4 (#251)

BenchmarkClaude Sonnet 4.5Phi-4
LMArena Instruction Following14591201
LiveBench Instruction Following—58.4%
IFEval85%—

Long Context Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 45.2 (#46), Phi-4: 36.9 (#226)

BenchmarkClaude Sonnet 4.5Phi-4
LMArena Longer Query14761217

Writing & Preference Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 66.5 (#34), Phi-4: 40.5 (#244)

BenchmarkClaude Sonnet 4.5Phi-4
LMArena Text14391217
LMArena Creative Writing14421182
LMArena Multi-Turn14651206
Short-Story Creative Writing—62.6%
EQ-Bench Creative Writing1678—
WildBench85.4%—
LiveBench Language—25.6%

Frequently asked questions

Is Claude Sonnet 4.5 better than Phi-4?

Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 31.2 on the Noometry Index. Phi-4 costs 69× 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 Phi-4?

Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.

Is Claude Sonnet 4.5 or Phi-4 better for coding?

Claude Sonnet 4.5 scores higher on coding benchmarks: 47.3 versus 34.4 in the Noometry coding category.

Which has the bigger context window?

Claude Sonnet 4.5 does, with 200K tokens against 128K.

How many benchmarks do Claude Sonnet 4.5 and Phi-4 share?

24 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Phi-4 has 37.

Related comparisons

Go deeper