Model comparison

Mistral Medium 3.5 vs Phi-4 Mini

Mistral Medium 3.5 is the stronger model overall, scoring 39.6 to 30.4 on the Noometry Index. Phi-4 Mini costs 23× less per token, which makes it the better buy when Mistral Medium 3.5's lead doesn't matter for your workload.

Last verified October 10, 2026. 0 shared benchmarks.

Mistral Medium 3.5

Mistral AI

39.6

Rank #151 Confirmed

Phi-4 Mini

Microsoft

30.4

Rank #280 Reported

Summary

The widest gap is in knowledge, where Mistral Medium 3.5 leads 39.3 to 24.8.
Phi-4 Mini is cheaper at $0.075 / $0.30 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
Mistral Medium 3.5 accepts more context: 262K tokens versus 128K.

Side by side

Mistral Medium 3.5 and Phi-4 Mini specifications
	Mistral Medium 3.5	Phi-4 Mini
Provider	Mistral AI	Microsoft
Noometry Index	39.6	30.4
Released	—	2024-12-11
Weights	Open	Open
Context window	262K	128K
Max output	210K	4K
Input $ / M tokens	$1.50	$0.075
Output $ / M tokens	$7.50	$0.30
Results tracked	22	3

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

Category by category

Coding Mistral Medium 3.5 leads

Mistral Medium 3.5: 35.7 (#208), Phi-4 Mini: 27.6 (#312)

Coding benchmarks
Benchmark	Mistral Medium 3.5	Phi-4 Mini
LMArena WebDev	1263	—
SciCode	—	10.8%
LMArena Coding	1461	—

Reasoning Phi-4 Mini leads

Mistral Medium 3.5: 16.6 (#290), Phi-4 Mini: 21.7 (#190)

Reasoning benchmarks
Benchmark	Mistral Medium 3.5	Phi-4 Mini
Kagi LLM Benchmark	41.4%	—
NYT Connections (extended)	12.9%	—
CritPt	—	0%
LMArena Hard Prompts	1436	—
Epoch Capabilities Index	141.42	—

Math Not comparable

Mistral Medium 3.5: 36.4 (#113), Phi-4 Mini: —

Math benchmarks
Benchmark	Mistral Medium 3.5	Phi-4 Mini
LMArena Math	1432	—

Knowledge Mistral Medium 3.5 leads

Mistral Medium 3.5: 39.3 (#123), Phi-4 Mini: 24.8 (#261)

Knowledge benchmarks
Benchmark	Mistral Medium 3.5	Phi-4 Mini
Vectara Hallucination Rate	—	23.5%
LMArena Expert	1431	—

Multimodal Not comparable

Mistral Medium 3.5: 37.6 (#64), Phi-4 Mini: —

Multimodal benchmarks
Benchmark	Mistral Medium 3.5	Phi-4 Mini
LMArena Vision	1222	—

Multilingual Not comparable

Mistral Medium 3.5: 52.1 (#93), Phi-4 Mini: —

Multilingual benchmarks
Benchmark	Mistral Medium 3.5	Phi-4 Mini
LMArena Non-English	1405	—
LMArena Chinese	1443	—
LMArena French	1448	—
LMArena German	1453	—
LMArena Korean	1387	—
LMArena Russian	1396	—
LMArena Spanish	1406	—

Instruction Following Not comparable

Mistral Medium 3.5: 74.7 (#87), Phi-4 Mini: —

Instruction Following benchmarks
Benchmark	Mistral Medium 3.5	Phi-4 Mini
LMArena Instruction Following	1414	—

Long Context Not comparable

Mistral Medium 3.5: 43.2 (#101), Phi-4 Mini: —

Long Context benchmarks
Benchmark	Mistral Medium 3.5	Phi-4 Mini
LMArena Longer Query	1414	—

Writing & Preference Not comparable

Mistral Medium 3.5: 58.6 (#113), Phi-4 Mini: —

Writing & Preference benchmarks
Benchmark	Mistral Medium 3.5	Phi-4 Mini
LMArena Text	1421	—
LMArena Creative Writing	1372	—
EQ-Bench 4	993	—
LMArena Multi-Turn	1423	—

Frequently asked questions

Is Mistral Medium 3.5 better than Phi-4 Mini?

Which is cheaper, Mistral Medium 3.5 or Phi-4 Mini?

Phi-4 Mini is cheaper. It lists at $0.075 per million input tokens and $0.30 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.

Is Mistral Medium 3.5 or Phi-4 Mini better for coding?

Mistral Medium 3.5 scores higher on coding benchmarks: 35.7 versus 27.6 in the Noometry coding category.

Which has the bigger context window?

Mistral Medium 3.5 does, with 262K tokens against 128K.

How many benchmarks do Mistral Medium 3.5 and Phi-4 Mini share?

0 benchmarks have published results for both models. Mistral Medium 3.5 has 22 scored results on Noometry and Phi-4 Mini has 3.