Model comparison

GPT-5.4 nano vs MiniMax-M3

MiniMax-M3 is the stronger model overall, scoring 43.5 to 41.9 on the Noometry Index.

Last verified October 10, 2026. 30 shared benchmarks.

GPT-5.4 nano OpenAI

41.9

Rank #111 Confirmed

MiniMax-M3

MiniMax

43.5

Rank #81 Confirmed

Summary

They share 30 benchmarks with published results for both. GPT-5.4 nano scores higher in 2 categories and MiniMax-M3 in 7 categories; 9 gaps are clear of the uncertainty.
The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 41.8.
The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 87.8% for GPT-5.4 nano and 71.1% for MiniMax-M3.
GPT-5.4 nano is cheaper at $0.20 / $1.25 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M3.
MiniMax-M3 accepts more context: 1M tokens versus 400K.
MiniMax-M3 has downloadable open weights; the other is API-only.

Side by side

GPT-5.4 nano and MiniMax-M3 specifications
	GPT-5.4 nano	MiniMax-M3
Provider	OpenAI	MiniMax
Noometry Index	41.9	43.5
Released	2026-03-17	2026-06-01
Weights	Proprietary	Open
Context window	400K	1M
Max output	128K	512K
Input $ / M tokens	$0.20	$0.30
Output $ / M tokens	$1.25	$1.20
Results tracked	40	41

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

Category by category

Coding GPT-5.4 nano leads

GPT-5.4 nano: 43.1 (#82), MiniMax-M3: 41.5 (#111)

Coding benchmarks
Benchmark	GPT-5.4 nano	MiniMax-M3
SciCode	46.9%	47.1%
LMArena Coding	1404	1470
ALE-Bench	1,005	640.02
FrontierCode	—	14.7%
LMArena WebDev	—	1482
WeirdML	49.2%	—

Agentic & Tool Use Not comparable

GPT-5.4 nano: —, MiniMax-M3: 22.5 (#121)

Agentic & Tool Use benchmarks
Benchmark	GPT-5.4 nano	MiniMax-M3
APEX-Agents	—	37.7%
OSWorld 2.0	—	4.6%
GBAEval	—	0.9%
Vending-Bench 2	—	2,158

Reasoning MiniMax-M3 leads

GPT-5.4 nano: 23.8 (#159), MiniMax-M3: 29.3 (#83)

Reasoning benchmarks
Benchmark	GPT-5.4 nano	MiniMax-M3
CritPt	9.3%	3.7%
Chess Puzzles	30%	14%
LMArena Hard Prompts	1380	1447
Mystery Game Puzzles	9%	8%
DTBench	80.3%	78.9%
LMCA	36.9%	33.7%
Epoch Capabilities Index	145.78	147
ForecastBench	57.3	61.4
ARC-AGI-2	5.7%	—
SimpleBench	—	45.8%
Kagi LLM Benchmark	39.7%	—
NYT Connections (extended)	—	65.1%
ARC-AGI-1	51.5%	—
Surface Evolver Bench	—	55%

Math GPT-5.4 nano leads

GPT-5.4 nano: 40.7 (#76), MiniMax-M3: 39.1 (#83)

Math benchmarks
Benchmark	GPT-5.4 nano	MiniMax-M3
OTIS Mock AIME 2024-2025	87.8%	71.1%
ProofBench	5%	18%
LMArena Math	1406	1432
FrontierMath (Tiers 1-3)	44.9%	—
FrontierMath Tier 4	12.2%	—
FrontierMath (Feb 2025 set)	25.9%	—
FrontierMath Tier 4 (v1)	6.3%	—

Knowledge MiniMax-M3 leads

GPT-5.4 nano: 41.8 (#94), MiniMax-M3: 58.4 (#32)

Knowledge benchmarks
Benchmark	GPT-5.4 nano	MiniMax-M3
GPQA Diamond	78.5%	90.9%
LMArena Expert	1397	1462
SimpleQA Verified	11.7%	—
Vectara Hallucination Rate	3.1%	—

Multimodal MiniMax-M3 leads

GPT-5.4 nano: 36.0 (#73), MiniMax-M3: 39.5 (#45)

Multimodal benchmarks
Benchmark	GPT-5.4 nano	MiniMax-M3
LMArena Vision	1196	1254
LMArena Document	—	1435

Multilingual MiniMax-M3 leads

GPT-5.4 nano: 48.8 (#136), MiniMax-M3: 53.2 (#70)

Multilingual benchmarks
Benchmark	GPT-5.4 nano	MiniMax-M3
LMArena Non-English	1359	1420
LMArena Chinese	1391	1465
LMArena French	1396	1445
LMArena German	1368	1424
LMArena Japanese	1342	1381
LMArena Korean	1321	1372
LMArena Russian	1363	1430
LMArena Spanish	1368	1431

Instruction Following MiniMax-M3 leads

GPT-5.4 nano: 72.1 (#139), MiniMax-M3: 75.7 (#56)

Instruction Following benchmarks
Benchmark	GPT-5.4 nano	MiniMax-M3
LMArena Instruction Following	1362	1433

Long Context MiniMax-M3 leads

GPT-5.4 nano: 41.6 (#131), MiniMax-M3: 44.2 (#68)

Long Context benchmarks
Benchmark	GPT-5.4 nano	MiniMax-M3
LMArena Longer Query	1365	1445

Writing & Preference MiniMax-M3 leads

GPT-5.4 nano: 55.9 (#137), MiniMax-M3: 62.3 (#79)

Writing & Preference benchmarks
Benchmark	GPT-5.4 nano	MiniMax-M3
LMArena Text	1372	1433
LMArena Creative Writing	1313	1405
LMArena Multi-Turn	1382	1441
EQ-Bench 4	—	1150

Frequently asked questions

Is GPT-5.4 nano better than MiniMax-M3?

MiniMax-M3 is the stronger model overall, scoring 43.5 to 41.9 on the Noometry Index.

Which is cheaper, GPT-5.4 nano or MiniMax-M3?

GPT-5.4 nano is cheaper. It lists at $0.20 per million input tokens and $1.25 per million output tokens; MiniMax-M3 lists at $0.30 and $1.20.

Is GPT-5.4 nano or MiniMax-M3 better for coding?

GPT-5.4 nano scores higher on coding benchmarks: 43.1 versus 41.5 in the Noometry coding category.

Which has the bigger context window?

MiniMax-M3 does, with 1M tokens against 400K.

How many benchmarks do GPT-5.4 nano and MiniMax-M3 share?

30 benchmarks have published results for both models. GPT-5.4 nano has 40 scored results on Noometry and MiniMax-M3 has 41.