Noometry

Model comparison

Mistral 7B vs Phi-4

Phi-4 is the stronger model overall, scoring 31.2 to 23.0 on the Noometry Index.

Last verified . 24 shared benchmarks.

Mistral 7B Mistral AI

23.0

Rank #351 Confirmed

Phi-4 Microsoft

31.2

Rank #279 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Mistral 7B scores higher in 0 categories and Phi-4 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Phi-4 leads 32.6 to 7.4.
  • The biggest single-benchmark swing is MATH Level 5: 3.7% for Mistral 7B and 64.9% for Phi-4.
  • Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $0.25 / $0.25 for Mistral 7B.
  • Phi-4 accepts more context: 128K tokens versus 8K.

Side by side

Mistral 7BPhi-4
ProviderMistral AIMicrosoft
Noometry Index23.031.2
Released2023-09-272024-12-11
WeightsOpenOpen
Context window8K128K
Max output8K4K
Input $ / M tokens$0.25$0.07
Output $ / M tokens$0.25$0.14
Results tracked3737

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

Category by category

Coding Phi-4 leads

Mistral 7B: 26.4 (#326), Phi-4: 34.4 (#239)

BenchmarkMistral 7BPhi-4
BigCodeBench Instruct19.5%45.5%
LMArena Coding10821231
BigCodeBench Complete27.3%55.4%
LiveBench Coding—30.7%
HumanEval+36%—
MBPP+42.1%—

Agentic & Tool Use Not comparable

Mistral 7B: —, Phi-4: 22.8 (#128)

BenchmarkMistral 7BPhi-4
Berkeley Function Calling Leaderboard—28.8%
BALROG—11.6%

Reasoning Phi-4 leads

Mistral 7B: 13.1 (#336), Phi-4: 17.7 (#291)

BenchmarkMistral 7BPhi-4
Chess Puzzles0%1%
LMArena Hard Prompts10671220
Epoch Capabilities Index112.21130.42
LiveBench Reasoning—47.8%
DTBench42.5%—
LiveBench Data Analysis—45.2%
Adversarial NLI47.1%—
BIG-Bench Hard56.1%—
HellaSwag81%—
LiveBench—41.6%
PIQA83%—
WinoGrande75.3%—

Math Phi-4 leads

Mistral 7B: 8.1 (#325), Phi-4: 20.8 (#285)

BenchmarkMistral 7BPhi-4
OTIS Mock AIME 2024-20250.3%13.8%
LMArena Math10851246
MATH Level 53.7%64.9%
LiveBench Math—42%
GSM8K54.4%—

Knowledge Phi-4 leads

Mistral 7B: 7.4 (#311), Phi-4: 32.6 (#209)

BenchmarkMistral 7BPhi-4
GPQA Diamond15.2%56.1%
LMArena Expert10361203
MMLU62.5%84.8%
Confabulations—29.4%
Vectara Hallucination Rate—3.7%
ARC (AI2) Challenge78.6%—
BoolQ87.4%—
OpenBookQA79.8%—
TriviaQA75.2%—

Multilingual Phi-4 leads

Mistral 7B: 25.8 (#283), Phi-4: 37.2 (#237)

BenchmarkMistral 7BPhi-4
LMArena Non-English10121197
LMArena Chinese10091212
LMArena French10371224
LMArena German9871222
LMArena Japanese8781158
LMArena Russian10181209
LMArena Spanish10261234
LMArena Korean—1151

Instruction Following Phi-4 leads

Mistral 7B: 54.2 (#280), Phi-4: 60.4 (#251)

BenchmarkMistral 7BPhi-4
LMArena Instruction Following10601201
LiveBench Instruction Following—58.4%

Long Context Phi-4 leads

Mistral 7B: 32.2 (#271), Phi-4: 36.9 (#226)

BenchmarkMistral 7BPhi-4
LMArena Longer Query10601217

Writing & Preference Phi-4 leads

Mistral 7B: 30.7 (#286), Phi-4: 40.5 (#244)

BenchmarkMistral 7BPhi-4
LMArena Text10901217
LMArena Creative Writing10681182
LMArena Multi-Turn10621206
Short-Story Creative Writing—62.6%
LiveBench Language—25.6%

Frequently asked questions

Is Mistral 7B better than Phi-4?

Phi-4 is the stronger model overall, scoring 31.2 to 23.0 on the Noometry Index.

Which is cheaper, Mistral 7B or Phi-4?

Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; Mistral 7B lists at $0.25 and $0.25.

Is Mistral 7B or Phi-4 better for coding?

Phi-4 scores higher on coding benchmarks: 34.4 versus 26.4 in the Noometry coding category.

Which has the bigger context window?

Phi-4 does, with 128K tokens against 8K.

How many benchmarks do Mistral 7B and Phi-4 share?

24 benchmarks have published results for both models. Mistral 7B has 37 scored results on Noometry and Phi-4 has 37.

Related comparisons

Go deeper