Model comparison

MiniMax M1 vs Phi-4

MiniMax M1 is the stronger model overall, scoring 40.3 to 31.2 on the Noometry Index. Phi-4 costs 11× less per token, which makes it the better buy when MiniMax M1's lead doesn't matter for your workload.

Last verified October 10, 2026. 17 shared benchmarks.

MiniMax M1

MiniMax

40.3

Rank #150 Confirmed

Phi-4

Microsoft

31.2

Rank #279 Confirmed

Summary

They share 17 benchmarks with published results for both. MiniMax M1 scores higher in 8 categories and Phi-4 in 0 categories; 8 gaps are clear of the uncertainty.
The widest gap is in math, where MiniMax M1 leads 37.5 to 20.8.
Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $0.55 / $2.20 for MiniMax M1.
MiniMax M1 accepts more context: 1M tokens versus 128K.

Side by side

MiniMax M1 and Phi-4 specifications
	MiniMax M1	Phi-4
Provider	MiniMax	Microsoft
Noometry Index	40.3	31.2
Released	2025-06-13	2024-12-11
Weights	Open	Open
Context window	1M	128K
Max output	40K	4K
Input $ / M tokens	$0.55	$0.07
Output $ / M tokens	$2.20	$0.14
Results tracked	18	37

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

Category by category

Coding MiniMax M1 leads

MiniMax M1: 39.9 (#153), Phi-4: 34.4 (#239)

Coding benchmarks
Benchmark	MiniMax M1	Phi-4
LMArena Coding	1359	1231
BigCodeBench Instruct	—	45.5%
LiveBench Coding	—	30.7%
BigCodeBench Complete	—	55.4%

Agentic & Tool Use Not comparable

MiniMax M1: —, Phi-4: 22.8 (#128)

Agentic & Tool Use benchmarks
Benchmark	MiniMax M1	Phi-4
Berkeley Function Calling Leaderboard	—	28.8%
BALROG	—	11.6%

Reasoning MiniMax M1 leads

MiniMax M1: 26.9 (#126), Phi-4: 17.7 (#291)

Reasoning benchmarks
Benchmark	MiniMax M1	Phi-4
LMArena Hard Prompts	1339	1220
Chess Puzzles	—	1%
LiveBench Reasoning	—	47.8%
LiveBench Data Analysis	—	45.2%
Epoch Capabilities Index	—	130.42
LiveBench	—	41.6%

Math MiniMax M1 leads

MiniMax M1: 37.5 (#151), Phi-4: 20.8 (#285)

Math benchmarks
Benchmark	MiniMax M1	Phi-4
LMArena Math	1361	1246
OTIS Mock AIME 2024-2025	—	13.8%
LiveBench Math	—	42%
MATH Level 5	—	64.9%

Knowledge MiniMax M1 leads

MiniMax M1: 36.4 (#170), Phi-4: 32.6 (#209)

Knowledge benchmarks
Benchmark	MiniMax M1	Phi-4
LMArena Expert	1317	1203
GPQA Diamond	—	56.1%
Confabulations	—	29.4%
Vectara Hallucination Rate	—	3.7%
MMLU	—	84.8%

Multilingual MiniMax M1 leads

MiniMax M1: 45.8 (#163), Phi-4: 37.2 (#237)

Multilingual benchmarks
Benchmark	MiniMax M1	Phi-4
LMArena Non-English	1319	1197
LMArena Chinese	1360	1212
LMArena French	1370	1224
LMArena German	1350	1222
LMArena Japanese	1217	1158
LMArena Korean	1266	1151
LMArena Russian	1329	1209
LMArena Spanish	1353	1234

Instruction Following MiniMax M1 leads

MiniMax M1: 69.3 (#174), Phi-4: 60.4 (#251)

Instruction Following benchmarks
Benchmark	MiniMax M1	Phi-4
LMArena Instruction Following	1312	1201
LiveBench Instruction Following	—	58.4%

Long Context MiniMax M1 leads

MiniMax M1: 41.4 (#141), Phi-4: 36.9 (#226)

Long Context benchmarks
Benchmark	MiniMax M1	Phi-4
LMArena Longer Query	1326	1217
Fiction.LiveBench	69.4%	—

Writing & Preference MiniMax M1 leads

MiniMax M1: 53.1 (#161), Phi-4: 40.5 (#244)

Writing & Preference benchmarks
Benchmark	MiniMax M1	Phi-4
LMArena Text	1343	1217
LMArena Creative Writing	1298	1182
LMArena Multi-Turn	1335	1206
Short-Story Creative Writing	—	62.6%
LiveBench Language	—	25.6%

Frequently asked questions

Is MiniMax M1 better than Phi-4?

Which is cheaper, MiniMax M1 or Phi-4?

Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; MiniMax M1 lists at $0.55 and $2.20.

Is MiniMax M1 or Phi-4 better for coding?

MiniMax M1 scores higher on coding benchmarks: 39.9 versus 34.4 in the Noometry coding category.

Which has the bigger context window?

MiniMax M1 does, with 1M tokens against 128K.

How many benchmarks do MiniMax M1 and Phi-4 share?

17 benchmarks have published results for both models. MiniMax M1 has 18 scored results on Noometry and Phi-4 has 37.