Model comparison

GPT-4 vs MiniMax M1

MiniMax M1 is the stronger model overall, scoring 40.3 to 29.1 on the Noometry Index.

Last verified October 10, 2026. 17 shared benchmarks.

GPT-4 OpenAI

29.1

Rank #316 Confirmed

MiniMax M1

MiniMax

40.3

Rank #150 Confirmed

Summary

They share 17 benchmarks with published results for both. GPT-4 scores higher in 0 categories and MiniMax M1 in 8 categories; 8 gaps are clear of the uncertainty.
The widest gap is in math, where MiniMax M1 leads 37.5 to 10.8.
MiniMax M1 is cheaper at $0.55 / $2.20 per million input/output tokens, against $30 / $60 for GPT-4.
MiniMax M1 accepts more context: 1M tokens versus 8K.
MiniMax M1 has downloadable open weights; the other is API-only.

Side by side

GPT-4 and MiniMax M1 specifications
	GPT-4	MiniMax M1
Provider	OpenAI	MiniMax
Noometry Index	29.1	40.3
Released	2023-03-14	2025-06-13
Weights	Proprietary	Open
Context window	8K	1M
Max output	8K	40K
Input $ / M tokens	$30	$0.55
Output $ / M tokens	$60	$2.20
Results tracked	38	18

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

Category by category

Coding MiniMax M1 leads

GPT-4: 31.6 (#283), MiniMax M1: 39.9 (#153)

Coding benchmarks
Benchmark	GPT-4	MiniMax M1
LMArena Coding	1254	1359
WeirdML	12.4%	—
BigCodeBench Instruct	46%	—
BigCodeBench Complete	57.2%	—
HumanEval+	79.3%	—

Agentic & Tool Use Not comparable

GPT-4: —, MiniMax M1: —

Agentic & Tool Use benchmarks
Benchmark	GPT-4	MiniMax M1
METR Time Horizons	36.1%	—

Reasoning MiniMax M1 leads

GPT-4: 17.8 (#289), MiniMax M1: 26.9 (#126)

Reasoning benchmarks
Benchmark	GPT-4	MiniMax M1
LMArena Hard Prompts	1241	1339
Chess Puzzles	4%	—
Mystery Game Puzzles	12%	—
DTBench	62.7%	—
LMCA	17.1%	—
BIG-Bench Hard	75.1%	—
Epoch Capabilities Index	125.89	—
ForecastBench	57.8	—
HellaSwag	95.3%	—
WinoGrande	87.5%	—

Math MiniMax M1 leads

GPT-4: 10.8 (#309), MiniMax M1: 37.5 (#151)

Math benchmarks
Benchmark	GPT-4	MiniMax M1
LMArena Math	1269	1361
OTIS Mock AIME 2024-2025	1.1%	—
MATH Level 5	23%	—
GSM8K	92%	—

Knowledge MiniMax M1 leads

GPT-4: 18.4 (#282), MiniMax M1: 36.4 (#170)

Knowledge benchmarks
Benchmark	GPT-4	MiniMax M1
LMArena Expert	1211	1317
GPQA Diamond	35.7%	—
MMLU	86.4%	—
TriviaQA	84.8%	—

Multilingual MiniMax M1 leads

GPT-4: 40.6 (#215), MiniMax M1: 45.8 (#163)

Multilingual benchmarks
Benchmark	GPT-4	MiniMax M1
LMArena Non-English	1246	1319
LMArena Chinese	1242	1360
LMArena French	1283	1370
LMArena German	1251	1350
LMArena Japanese	1209	1217
LMArena Korean	1184	1266
LMArena Russian	1251	1329
LMArena Spanish	1261	1353

Instruction Following MiniMax M1 leads

GPT-4: 65.3 (#222), MiniMax M1: 69.3 (#174)

Instruction Following benchmarks
Benchmark	GPT-4	MiniMax M1
LMArena Instruction Following	1241	1312

Long Context MiniMax M1 leads

GPT-4: 37.7 (#212), MiniMax M1: 41.4 (#141)

Long Context benchmarks
Benchmark	GPT-4	MiniMax M1
LMArena Longer Query	1244	1326
Fiction.LiveBench	—	69.4%

Writing & Preference MiniMax M1 leads

GPT-4: 34.9 (#268), MiniMax M1: 53.1 (#161)

Writing & Preference benchmarks
Benchmark	GPT-4	MiniMax M1
LMArena Text	1263	1343
LMArena Creative Writing	1244	1298
LMArena Multi-Turn	1257	1335
EQ-Bench Creative Writing	752	—

Frequently asked questions

Is GPT-4 better than MiniMax M1?

MiniMax M1 is the stronger model overall, scoring 40.3 to 29.1 on the Noometry Index.

Which is cheaper, GPT-4 or MiniMax M1?

MiniMax M1 is cheaper. It lists at $0.55 per million input tokens and $2.20 per million output tokens; GPT-4 lists at $30 and $60.

Is GPT-4 or MiniMax M1 better for coding?

MiniMax M1 scores higher on coding benchmarks: 39.9 versus 31.6 in the Noometry coding category.

Which has the bigger context window?

MiniMax M1 does, with 1M tokens against 8K.

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

17 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and MiniMax M1 has 18.