Model comparison

GLM-4.6 vs MiniMax-M2.1

GLM-4.6 is the stronger model overall, scoring 41.4 to 38.9 on the Noometry Index. MiniMax-M2.1 costs 1.9× less per token, which makes it the better buy when GLM-4.6's lead doesn't matter for your workload.

Last verified October 11, 2026. 21 shared benchmarks.

GLM-4.6 Z.ai (Zhipu)

41.4

Rank #135 Confirmed

MiniMax-M2.1

MiniMax

38.9

Rank #178 Confirmed

Summary

They share 21 benchmarks with published results for both. GLM-4.6 scores higher in 8 categories and MiniMax-M2.1 in 1 category; 5 gaps are clear of the uncertainty.
The widest gap is in reasoning, where GLM-4.6 leads 23.7 to 16.6.
The biggest single-benchmark swing is Terminal-Bench: 24.5% for GLM-4.6 and 36.6% for MiniMax-M2.1.
MiniMax-M2.1 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.60 / $2.20 for GLM-4.6.

Side by side

GLM-4.6 and MiniMax-M2.1 specifications
	GLM-4.6	MiniMax-M2.1
Provider	Z.ai (Zhipu)	MiniMax
Noometry Index	41.4	38.9
Released	2025-09-30	2025-12-23
Weights	Open	Open
Context window	205K	205K
Max output	131K	131K
Input $ / M tokens	$0.60	$0.30
Output $ / M tokens	$2.20	$1.20
Results tracked	29	22

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

Category by category

Coding Too close to call

GLM-4.6: 40.1 (#148), MiniMax-M2.1: 40.4 (#143)

Coding benchmarks
Benchmark	GLM-4.6	MiniMax-M2.1
LMArena WebDev	1340	1384
LMArena Coding	1449	1421
ALE-Bench	340.82	623.83
SWE-bench Verified (bash only)	55.4%	—
SciCode	38.4%	—

Agentic & Tool Use GLM-4.6 leads

GLM-4.6: 32.3 (#66), MiniMax-M2.1: 27.9 (#98)

Agentic & Tool Use benchmarks
Benchmark	GLM-4.6	MiniMax-M2.1
Terminal-Bench	24.5%	36.6%
Berkeley Function Calling Leaderboard	72.4%	—

Reasoning GLM-4.6 leads

GLM-4.6: 23.7 (#172), MiniMax-M2.1: 16.6 (#302)

Reasoning benchmarks
Benchmark	GLM-4.6	MiniMax-M2.1
LMArena Hard Prompts	1440	1411
Kagi LLM Benchmark	47.4%	—
NYT Connections (extended)	—	11.2%
CritPt	1.1%	—

Math Too close to call

GLM-4.6: 39.1 (#111), MiniMax-M2.1: 38.3 (#138)

Math benchmarks
Benchmark	GLM-4.6	MiniMax-M2.1
LMArena Math	1432	1397
FrontierMath (Feb 2025 set)	3.8%	—
FrontierMath Tier 4 (v1)	2.1%	—

Knowledge GLM-4.6 leads

GLM-4.6: 40.2 (#124), MiniMax-M2.1: 38.3 (#147)

Knowledge benchmarks
Benchmark	GLM-4.6	MiniMax-M2.1
Vectara Hallucination Rate	9.5%	11.8%
LMArena Expert	1431	1431

Multilingual GLM-4.6 leads

GLM-4.6: 53.5 (#66), MiniMax-M2.1: 50.0 (#128)

Multilingual benchmarks
Benchmark	GLM-4.6	MiniMax-M2.1
LMArena Non-English	1426	1378
LMArena Chinese	1499	1430
LMArena French	1459	1404
LMArena German	1447	1381
LMArena Japanese	1393	1287
LMArena Korean	1400	1298
LMArena Russian	1419	1387
LMArena Spanish	1436	1397

Instruction Following Too close to call

GLM-4.6: 74.3 (#98), MiniMax-M2.1: 73.8 (#112)

Instruction Following benchmarks
Benchmark	GLM-4.6	MiniMax-M2.1
LMArena Instruction Following	1410	1400

Long Context Too close to call

GLM-4.6: 43.4 (#94), MiniMax-M2.1: 43.2 (#101)

Long Context benchmarks
Benchmark	GLM-4.6	MiniMax-M2.1
LMArena Longer Query	1422	1416

Writing & Preference GLM-4.6 leads

GLM-4.6: 61.1 (#90), MiniMax-M2.1: 58.3 (#120)

Writing & Preference benchmarks
Benchmark	GLM-4.6	MiniMax-M2.1
LMArena Text	1440	1392
LMArena Creative Writing	1411	1361
LMArena Multi-Turn	1427	1396
EQ-Bench Creative Writing	1411	—

Frequently asked questions

Is GLM-4.6 better than MiniMax-M2.1?

Which is cheaper, GLM-4.6 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; GLM-4.6 lists at $0.60 and $2.20.

Is GLM-4.6 or MiniMax-M2.1 better for coding?

They score almost the same on coding (40.1 vs 40.4); test both on your own repository before choosing.

Which has the bigger context window?

Both accept 205K tokens.

How many benchmarks do GLM-4.6 and MiniMax-M2.1 share?

21 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and MiniMax-M2.1 has 22.