Model comparison

GPT-5.2 Codex vs MiniMax-M2.1

GPT-5.2 Codex is the stronger model overall, scoring 42.2 to 38.4 on the Noometry Index. MiniMax-M2.1 costs 9.2× less per token, which makes it the better buy when GPT-5.2 Codex's lead doesn't matter for your workload.

Last verified October 10, 2026. 3 shared benchmarks.

GPT-5.2 Codex OpenAI

42.2

Rank #107 Reported

MiniMax-M2.1

MiniMax

38.4

Rank #177 Confirmed

Summary

They share 3 benchmarks with published results for both. GPT-5.2 Codex scores higher in 2 categories and MiniMax-M2.1 in 0 categories; 2 gaps are clear of the uncertainty.
The widest gap is in agentic & tool use, where GPT-5.2 Codex leads 40.7 to 27.7.
The biggest single-benchmark swing is Terminal-Bench: 66.5% for GPT-5.2 Codex and 36.6% for MiniMax-M2.1.
MiniMax-M2.1 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1.75 / $14 for GPT-5.2 Codex.
GPT-5.2 Codex accepts more context: 400K tokens versus 205K.
MiniMax-M2.1 has downloadable open weights; the other is API-only.

Side by side

GPT-5.2 Codex and MiniMax-M2.1 specifications
	GPT-5.2 Codex	MiniMax-M2.1
Provider	OpenAI	MiniMax
Noometry Index	42.2	38.4
Released	2025-12-18	2025-12-23
Weights	Proprietary	Open
Context window	400K	205K
Max output	128K	131K
Input $ / M tokens	$1.75	$0.30
Output $ / M tokens	$14	$1.20
Results tracked	5	22

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

Category by category

Coding GPT-5.2 Codex leads

GPT-5.2 Codex: 45.4 (#66), MiniMax-M2.1: 40.1 (#132)

Coding benchmarks
Benchmark	GPT-5.2 Codex	MiniMax-M2.1
LMArena WebDev	1339	1384
ALE-Bench	1,300	623.83
SWE-bench Verified (bash only)	72.8%	—
SWE-bench Multilingual	66.3%	—
LMArena Coding	—	1421

Agentic & Tool Use GPT-5.2 Codex leads

GPT-5.2 Codex: 40.7 (#20), MiniMax-M2.1: 27.7 (#91)

Agentic & Tool Use benchmarks
Benchmark	GPT-5.2 Codex	MiniMax-M2.1
Terminal-Bench	66.5%	36.6%

Reasoning Not comparable

GPT-5.2 Codex: —, MiniMax-M2.1: 15.8 (#301)

Reasoning benchmarks
Benchmark	GPT-5.2 Codex	MiniMax-M2.1
NYT Connections (extended)	—	11.2%
LMArena Hard Prompts	—	1410

Math Not comparable

GPT-5.2 Codex: —, MiniMax-M2.1: 35.6 (#142)

Math benchmarks
Benchmark	GPT-5.2 Codex	MiniMax-M2.1
LMArena Math	—	1396

Knowledge Not comparable

GPT-5.2 Codex: —, MiniMax-M2.1: 37.7 (#143)

Knowledge benchmarks
Benchmark	GPT-5.2 Codex	MiniMax-M2.1
Vectara Hallucination Rate	—	11.8%
LMArena Expert	—	1432

Multilingual Not comparable

GPT-5.2 Codex: —, MiniMax-M2.1: 50.2 (#123)

Multilingual benchmarks
Benchmark	GPT-5.2 Codex	MiniMax-M2.1
LMArena Non-English	—	1378
LMArena Chinese	—	1430
LMArena French	—	1405
LMArena German	—	1380
LMArena Japanese	—	1287
LMArena Korean	—	1297
LMArena Russian	—	1386
LMArena Spanish	—	1396

Instruction Following Not comparable

GPT-5.2 Codex: —, MiniMax-M2.1: 74.0 (#108)

Instruction Following benchmarks
Benchmark	GPT-5.2 Codex	MiniMax-M2.1
LMArena Instruction Following	—	1399

Long Context Not comparable

GPT-5.2 Codex: —, MiniMax-M2.1: 43.2 (#98)

Long Context benchmarks
Benchmark	GPT-5.2 Codex	MiniMax-M2.1
LMArena Longer Query	—	1416

Writing & Preference Not comparable

GPT-5.2 Codex: —, MiniMax-M2.1: 58.5 (#114)

Writing & Preference benchmarks
Benchmark	GPT-5.2 Codex	MiniMax-M2.1
LMArena Text	—	1392
LMArena Creative Writing	—	1362
LMArena Multi-Turn	—	1396

Frequently asked questions

Is GPT-5.2 Codex better than MiniMax-M2.1?

Which is cheaper, GPT-5.2 Codex or MiniMax-M2.1?

MiniMax-M2.1 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; GPT-5.2 Codex lists at $1.75 and $14.

Is GPT-5.2 Codex or MiniMax-M2.1 better for coding?

GPT-5.2 Codex scores higher on coding benchmarks: 45.4 versus 40.1 in the Noometry coding category.

Which has the bigger context window?

GPT-5.2 Codex does, with 400K tokens against 205K.

How many benchmarks do GPT-5.2 Codex and MiniMax-M2.1 share?

3 benchmarks have published results for both models. GPT-5.2 Codex has 5 scored results on Noometry and MiniMax-M2.1 has 22.