Noometry

Model comparison

C4ai Aya Expanse 8b vs Phi-4

C4ai Aya Expanse 8b is the stronger model overall, scoring 34.9 to 31.2 on the Noometry Index.

Last verified . 15 shared benchmarks.

C4ai Aya Expanse 8b Cohere

34.9

Rank #229 Confirmed

Phi-4 Microsoft

31.2

Rank #279 Confirmed

Summary

  • They share 15 benchmarks with published results for both. C4ai Aya Expanse 8b scores higher in 3 categories and Phi-4 in 5 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in math, where C4ai Aya Expanse 8b leads 33.3 to 20.8.
  • The biggest single-benchmark swing is Vectara Hallucination Rate: 9.5% for C4ai Aya Expanse 8b and 3.7% for Phi-4.

Side by side

C4ai Aya Expanse 8bPhi-4
ProviderCohereMicrosoft
Noometry Index34.931.2
Released—2024-12-11
WeightsOpenOpen
Context window—128K
Max output—4K
Input $ / M tokens—$0.07
Output $ / M tokens—$0.14
Results tracked1537

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

Category by category

Coding Too close to call

C4ai Aya Expanse 8b: 33.8 (#252), Phi-4: 34.4 (#239)

BenchmarkC4ai Aya Expanse 8bPhi-4
LMArena Coding11601231
BigCodeBench Instruct—45.5%
LiveBench Coding—30.7%
BigCodeBench Complete—55.4%

Agentic & Tool Use Not comparable

C4ai Aya Expanse 8b: —, Phi-4: 22.8 (#128)

BenchmarkC4ai Aya Expanse 8bPhi-4
Berkeley Function Calling Leaderboard—28.8%
BALROG—11.6%

Reasoning C4ai Aya Expanse 8b leads

C4ai Aya Expanse 8b: 22.4 (#197), Phi-4: 17.7 (#291)

BenchmarkC4ai Aya Expanse 8bPhi-4
LMArena Hard Prompts11561220
Chess Puzzles—1%
LiveBench Reasoning—47.8%
LiveBench Data Analysis—45.2%
Epoch Capabilities Index—130.42
LiveBench—41.6%

Math C4ai Aya Expanse 8b leads

C4ai Aya Expanse 8b: 33.3 (#203), Phi-4: 20.8 (#285)

BenchmarkC4ai Aya Expanse 8bPhi-4
LMArena Math11681246
OTIS Mock AIME 2024-2025—13.8%
LiveBench Math—42%
MATH Level 5—64.9%

Knowledge Too close to call

C4ai Aya Expanse 8b: 33.6 (#201), Phi-4: 32.6 (#209)

BenchmarkC4ai Aya Expanse 8bPhi-4
Vectara Hallucination Rate9.5%3.7%
LMArena Expert11531203
GPQA Diamond—56.1%
Confabulations—29.4%
MMLU—84.8%

Multilingual Phi-4 leads

C4ai Aya Expanse 8b: 36.1 (#242), Phi-4: 37.2 (#237)

BenchmarkC4ai Aya Expanse 8bPhi-4
LMArena Non-English11801197
LMArena Chinese11811212
LMArena German11881222
LMArena Japanese11201158
LMArena Russian11971209
LMArena French—1224
LMArena Korean—1151
LMArena Spanish—1234

Instruction Following Too close to call

C4ai Aya Expanse 8b: 60.1 (#253), Phi-4: 60.4 (#251)

BenchmarkC4ai Aya Expanse 8bPhi-4
LMArena Instruction Following11551201
LiveBench Instruction Following—58.4%

Long Context Too close to call

C4ai Aya Expanse 8b: 36.1 (#236), Phi-4: 36.9 (#226)

BenchmarkC4ai Aya Expanse 8bPhi-4
LMArena Longer Query11911217

Writing & Preference Phi-4 leads

C4ai Aya Expanse 8b: 39.0 (#250), Phi-4: 40.5 (#244)

BenchmarkC4ai Aya Expanse 8bPhi-4
LMArena Text11851217
LMArena Creative Writing11681182
LMArena Multi-Turn11601206
Short-Story Creative Writing—62.6%
LiveBench Language—25.6%

Frequently asked questions

Is C4ai Aya Expanse 8b better than Phi-4?

C4ai Aya Expanse 8b is the stronger model overall, scoring 34.9 to 31.2 on the Noometry Index.

Is C4ai Aya Expanse 8b or Phi-4 better for coding?

They score almost the same on coding (33.8 vs 34.4); test both on your own repository before choosing.

How many benchmarks do C4ai Aya Expanse 8b and Phi-4 share?

15 benchmarks have published results for both models. C4ai Aya Expanse 8b has 15 scored results on Noometry and Phi-4 has 37.

Related comparisons

Go deeper