Noometry

Model comparison

Claude 3 Sonnet vs Phi-4

Phi-4 is the stronger model overall, scoring 31.2 to 29.0 on the Noometry Index.

Last verified . 24 shared benchmarks.

Claude 3 Sonnet Anthropic

29.0

Rank #319 Confirmed

Phi-4 Microsoft

31.2

Rank #279 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Claude 3 Sonnet scores higher in 4 categories and Phi-4 in 4 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Phi-4 leads 32.6 to 21.1.
  • The biggest single-benchmark swing is MATH Level 5: 18.2% for Claude 3 Sonnet and 64.9% for Phi-4.
  • Phi-4 has downloadable open weights; the other is API-only.

Side by side

Claude 3 SonnetPhi-4
ProviderAnthropicMicrosoft
Noometry Index29.031.2
Released2024-02-292024-12-11
WeightsProprietaryOpen
Context window—128K
Max output—4K
Input $ / M tokens—$0.07
Output $ / M tokens—$0.14
Results tracked3037

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

Category by category

Coding Phi-4 leads

Claude 3 Sonnet: 29.6 (#302), Phi-4: 34.4 (#239)

BenchmarkClaude 3 SonnetPhi-4
BigCodeBench Instruct42.7%45.5%
LMArena Coding12231231
BigCodeBench Complete53.8%55.4%
WeirdML10.2%—
LiveBench Coding—30.7%
HumanEval+64%—
MBPP+69.3%—

Agentic & Tool Use Not comparable

Claude 3 Sonnet: —, Phi-4: 22.8 (#128)

BenchmarkClaude 3 SonnetPhi-4
Berkeley Function Calling Leaderboard—28.8%
BALROG—11.6%

Reasoning Claude 3 Sonnet leads

Claude 3 Sonnet: 20.5 (#237), Phi-4: 17.7 (#291)

BenchmarkClaude 3 SonnetPhi-4
LMArena Hard Prompts11971220
Epoch Capabilities Index120.7130.42
Chess Puzzles—1%
LiveBench Reasoning—47.8%
DTBench53.6%—
LiveBench Data Analysis—45.2%
LiveBench—41.6%
WinoGrande75.1%—

Math Phi-4 leads

Claude 3 Sonnet: 10.7 (#310), Phi-4: 20.8 (#285)

BenchmarkClaude 3 SonnetPhi-4
OTIS Mock AIME 2024-20252.5%13.8%
LMArena Math12131246
MATH Level 518.2%64.9%
LiveBench Math—42%

Knowledge Phi-4 leads

Claude 3 Sonnet: 21.1 (#276), Phi-4: 32.6 (#209)

BenchmarkClaude 3 SonnetPhi-4
GPQA Diamond40.6%56.1%
LMArena Expert11731203
MMLU75.9%84.8%
Confabulations—29.4%
Vectara Hallucination Rate—3.7%

Multimodal Not comparable

Claude 3 Sonnet: 25.2 (#125), Phi-4: —

BenchmarkClaude 3 SonnetPhi-4
LMArena Vision984—

Multilingual Too close to call

Claude 3 Sonnet: 37.8 (#234), Phi-4: 37.2 (#237)

BenchmarkClaude 3 SonnetPhi-4
LMArena Non-English12051197
LMArena Chinese11891212
LMArena French12291224
LMArena German12041222
LMArena Japanese11311158
LMArena Korean11281151
LMArena Russian12271209
LMArena Spanish12041234

Instruction Following Claude 3 Sonnet leads

Claude 3 Sonnet: 62.8 (#235), Phi-4: 60.4 (#251)

BenchmarkClaude 3 SonnetPhi-4
LMArena Instruction Following11991201
LiveBench Instruction Following—58.4%

Long Context Too close to call

Claude 3 Sonnet: 36.7 (#228), Phi-4: 36.9 (#226)

BenchmarkClaude 3 SonnetPhi-4
LMArena Longer Query12111217

Writing & Preference Claude 3 Sonnet leads

Claude 3 Sonnet: 42.1 (#238), Phi-4: 40.5 (#244)

BenchmarkClaude 3 SonnetPhi-4
LMArena Text12181217
LMArena Creative Writing11861182
LMArena Multi-Turn12271206
Short-Story Creative Writing—62.6%
LiveBench Language—25.6%

Frequently asked questions

Is Claude 3 Sonnet better than Phi-4?

Phi-4 is the stronger model overall, scoring 31.2 to 29.0 on the Noometry Index.

Is Claude 3 Sonnet or Phi-4 better for coding?

Phi-4 scores higher on coding benchmarks: 34.4 versus 29.6 in the Noometry coding category.

How many benchmarks do Claude 3 Sonnet and Phi-4 share?

24 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Phi-4 has 37.

Related comparisons

Go deeper