Model comparison

MiniMax-M2 vs MiniMax-M2.5

MiniMax-M2.5 is the stronger model overall, scoring 38.1 to 36.9 on the Noometry Index.

Last verified October 10, 2026. 21 shared benchmarks.

MiniMax-M2

MiniMax

36.9

Rank #201 Confirmed

MiniMax-M2.5

MiniMax

38.1

Rank #181 Confirmed

Summary

They share 21 benchmarks with published results for both. MiniMax-M2 scores higher in 3 categories and MiniMax-M2.5 in 6 categories; 8 gaps are clear of the uncertainty.
The widest gap is in coding, where MiniMax-M2.5 leads 47.9 to 39.1.
The biggest single-benchmark swing is SWE-bench Verified (bash only): 61% for MiniMax-M2 and 75.8% for MiniMax-M2.5.
Both cost about the same: $0.30 input and $1.20 output per million tokens.

Side by side

MiniMax-M2 and MiniMax-M2.5 specifications
	MiniMax-M2	MiniMax-M2.5
Provider	MiniMax	MiniMax
Noometry Index	36.9	38.1
Released	2025-10-27	2026-02-12
Weights	Open	Open
Context window	205K	205K
Max output	131K	131K
Input $ / M tokens	$0.30	$0.30
Output $ / M tokens	$1.20	$1.20
Results tracked	21	33

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

Category by category

Coding MiniMax-M2.5 leads

MiniMax-M2: 39.1 (#151), MiniMax-M2.5: 47.9 (#53)

Coding benchmarks
Benchmark	MiniMax-M2	MiniMax-M2.5
SWE-bench Verified (bash only)	61%	75.8%
LMArena WebDev	1297	1386
LMArena Coding	1370	1380
SWE-bench Multilingual	—	68.3%
ALE-Bench	—	618.17

Agentic & Tool Use MiniMax-M2.5 leads

MiniMax-M2: 24.9 (#102), MiniMax-M2.5: 30.2 (#70)

Agentic & Tool Use benchmarks
Benchmark	MiniMax-M2	MiniMax-M2.5
Terminal-Bench	30%	42.7%
Vending-Bench 2	160.6	-23.16

Reasoning MiniMax-M2 leads

MiniMax-M2: 18.6 (#256), MiniMax-M2.5: 17.6 (#281)

Reasoning benchmarks
Benchmark	MiniMax-M2	MiniMax-M2.5
Kagi LLM Benchmark	57.8%	55.2%
NYT Connections (extended)	14.8%	16.8%
LMArena Hard Prompts	1357	1372
ARC-AGI-2	—	4.9%
ARC-AGI-1	—	63.7%
Epoch Capabilities Index	—	146.68

Math MiniMax-M2 leads

MiniMax-M2: 34.6 (#158), MiniMax-M2.5: 25.8 (#242)

Math benchmarks
Benchmark	MiniMax-M2	MiniMax-M2.5
LMArena Math	1350	1378
ProofBench	—	4%

Knowledge MiniMax-M2.5 leads

MiniMax-M2: 36.3 (#160), MiniMax-M2.5: 38.6 (#132)

Knowledge benchmarks
Benchmark	MiniMax-M2	MiniMax-M2.5
LMArena Expert	1336	1378
Vectara Hallucination Rate	—	9.1%

Multilingual MiniMax-M2.5 leads

MiniMax-M2: 45.6 (#165), MiniMax-M2.5: 47.3 (#147)

Multilingual benchmarks
Benchmark	MiniMax-M2	MiniMax-M2.5
LMArena Non-English	1314	1338
LMArena Chinese	1367	1392
LMArena French	1336	1363
LMArena German	1366	1361
LMArena Russian	1332	1359
LMArena Spanish	1326	1354
LMArena Japanese	—	1169
LMArena Korean	—	1232

Instruction Following MiniMax-M2.5 leads

MiniMax-M2: 70.4 (#160), MiniMax-M2.5: 71.7 (#143)

Instruction Following benchmarks
Benchmark	MiniMax-M2	MiniMax-M2.5
LMArena Instruction Following	1329	1353

Long Context MiniMax-M2 leads

MiniMax-M2: 40.5 (#148), MiniMax-M2.5: 37.4 (#211)

Long Context benchmarks
Benchmark	MiniMax-M2	MiniMax-M2.5
LMArena Longer Query	1332	1367
CL-bench	—	11.4%
CL-bench Life	—	6.3%

Writing & Preference Too close to call

MiniMax-M2: 53.3 (#157), MiniMax-M2.5: 54.1 (#149)

Writing & Preference benchmarks
Benchmark	MiniMax-M2	MiniMax-M2.5
LMArena Text	1340	1359
LMArena Creative Writing	1288	1331
LMArena Multi-Turn	1362	1364
EQ-Bench Creative Writing	—	1361

Frequently asked questions

Is MiniMax-M2 better than MiniMax-M2.5?

MiniMax-M2.5 is the stronger model overall, scoring 38.1 to 36.9 on the Noometry Index.

Which is cheaper, MiniMax-M2 or MiniMax-M2.5?

MiniMax-M2.5 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; MiniMax-M2 lists at $0.30 and $1.20.

Is MiniMax-M2 or MiniMax-M2.5 better for coding?

MiniMax-M2.5 scores higher on coding benchmarks: 47.9 versus 39.1 in the Noometry coding category.

Which has the bigger context window?

Both accept 205K tokens.

How many benchmarks do MiniMax-M2 and MiniMax-M2.5 share?

21 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and MiniMax-M2.5 has 33.