Model comparison

MiniMax-M2.5 vs o3-mini

MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 36.7 on the Noometry Index.

Last verified October 11, 2026. 20 shared benchmarks.

MiniMax-M2.5

MiniMax

38.3

Rank #188 Confirmed

o3-mini OpenAI

36.7

Rank #212 Confirmed

Summary

They share 20 benchmarks with published results for both. MiniMax-M2.5 scores higher in 7 categories and o3-mini in 2 categories; 7 gaps are clear of the uncertainty.
The widest gap is in coding, where MiniMax-M2.5 leads 48.1 to 40.8.
The biggest single-benchmark swing is ARC-AGI-1: 63.7% for MiniMax-M2.5 and 34.5% for o3-mini.
MiniMax-M2.5 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1.10 / $4.40 for o3-mini.
MiniMax-M2.5 accepts more context: 205K tokens versus 200K.
MiniMax-M2.5 has downloadable open weights; the other is API-only.

Side by side

MiniMax-M2.5 and o3-mini specifications
	MiniMax-M2.5	o3-mini
Provider	MiniMax	OpenAI
Noometry Index	38.3	36.7
Released	2026-02-12	2024-12-20
Weights	Open	Proprietary
Context window	205K	200K
Max output	131K	100K
Input $ / M tokens	$0.30	$1.10
Output $ / M tokens	$1.20	$4.40
Results tracked	33	51

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

Category by category

Coding MiniMax-M2.5 leads

MiniMax-M2.5: 48.1 (#58), o3-mini: 40.8 (#132)

Coding benchmarks
Benchmark	MiniMax-M2.5	o3-mini
LMArena Coding	1381	1378
SWE-bench Verified (bash only)	75.8%	—
Aider Polyglot	—	60.4%
LMArena WebDev	1387	—
SWE-bench Multilingual	68.3%	—
SciCode	—	39.8%
GSO	—	1.3%
WeirdML	—	43.7%
LiveBench Coding	—	82.7%
CadEval	—	54%
ALE-Bench	618.17	—

Agentic & Tool Use Too close to call

MiniMax-M2.5: 30.4 (#77), o3-mini: 29.6 (#84)

Agentic & Tool Use benchmarks
Benchmark	MiniMax-M2.5	o3-mini
Terminal-Bench	42.7%	—
Cybench	—	22.5%
Vending-Bench 2	-23.16	—

Reasoning MiniMax-M2.5 leads

MiniMax-M2.5: 17.5 (#292), o3-mini: 16.3 (#305)

Reasoning benchmarks
Benchmark	MiniMax-M2.5	o3-mini
ARC-AGI-2	4.9%	3%
ARC-AGI-1	63.7%	34.5%
LMArena Hard Prompts	1372	1366
Epoch Capabilities Index	146.68	140.34
SimpleBench	—	22.8%
Kagi LLM Benchmark	55.2%	—
NYT Connections (extended)	16.8%	—
CritPt	—	0.3%
Chess Puzzles	—	17%
LiveBench Reasoning	—	89.6%
Mystery Game Puzzles	—	7%
DTBench	—	68.8%
LiveBench Data Analysis	—	70.6%
LMCA	—	19%
ForecastBench	—	59.6
LiveBench	—	75.9%

Math o3-mini leads

MiniMax-M2.5: 26.9 (#253), o3-mini: 28.1 (#244)

Math benchmarks
Benchmark	MiniMax-M2.5	o3-mini
LMArena Math	1378	1396
FrontierMath (Tiers 1-3)	—	18.6%
FrontierMath Tier 4	—	0%
OTIS Mock AIME 2024-2025	—	76.9%
ProofBench	4%	—
LiveBench Math	—	77.3%
MATH Level 5	—	96.5%
FrontierMath (Feb 2025 set)	—	12.4%
FrontierMath Tier 4 (v1)	—	4.2%

Knowledge Too close to call

MiniMax-M2.5: 39.2 (#135), o3-mini: 38.3 (#146)

Knowledge benchmarks
Benchmark	MiniMax-M2.5	o3-mini
LMArena Expert	1379	1364
GPQA Diamond	—	77%
SimpleQA Verified	—	15.3%
Confabulations	—	17.9%
Vectara Hallucination Rate	9.1%	—

Multilingual MiniMax-M2.5 leads

MiniMax-M2.5: 47.1 (#152), o3-mini: 45.7 (#164)

Multilingual benchmarks
Benchmark	MiniMax-M2.5	o3-mini
LMArena Non-English	1338	1319
LMArena Chinese	1393	1379
LMArena French	1362	1334
LMArena German	1362	1303
LMArena Japanese	1171	1286
LMArena Korean	1232	1314
LMArena Russian	1358	1304
LMArena Spanish	1354	1321

Instruction Following o3-mini leads

MiniMax-M2.5: 71.5 (#148), o3-mini: 75.1 (#72)

Instruction Following benchmarks
Benchmark	MiniMax-M2.5	o3-mini
LMArena Instruction Following	1353	1337
LiveBench Instruction Following	—	84.4%

Long Context MiniMax-M2.5 leads

MiniMax-M2.5: 37.5 (#216), o3-mini: 33.8 (#256)

Long Context benchmarks
Benchmark	MiniMax-M2.5	o3-mini
LMArena Longer Query	1366	1343
Fiction.LiveBench	—	50%
CL-bench	11.4%	—
CL-bench Life	6.3%	—

Writing & Preference MiniMax-M2.5 leads

MiniMax-M2.5: 53.9 (#153), o3-mini: 50.3 (#182)

Writing & Preference benchmarks
Benchmark	MiniMax-M2.5	o3-mini
LMArena Text	1359	1337
LMArena Creative Writing	1331	1286
LMArena Multi-Turn	1364	1320
Short-Story Creative Writing	—	61.7%
EQ-Bench Creative Writing	1361	—
LiveBench Language	—	50.7%

Frequently asked questions

Is MiniMax-M2.5 better than o3-mini?

MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 36.7 on the Noometry Index.

Which is cheaper, MiniMax-M2.5 or o3-mini?

MiniMax-M2.5 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; o3-mini lists at $1.10 and $4.40.

Is MiniMax-M2.5 or o3-mini better for coding?

MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 40.8 in the Noometry coding category.

Which has the bigger context window?

MiniMax-M2.5 does, with 205K tokens against 200K.

How many benchmarks do MiniMax-M2.5 and o3-mini share?

20 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and o3-mini has 51.