Model comparison

GPT-5-Codex vs MiniMax-M3

MiniMax-M3 is the stronger model overall, scoring 43.8 to 37.9 on the Noometry Index.

Last verified October 11, 2026. 0 shared benchmarks.

GPT-5-Codex OpenAI

37.9

Rank #192 Reported

MiniMax-M3

MiniMax

43.8

Rank #85 Confirmed

Summary

The widest gap is in agentic & tool use, where GPT-5-Codex leads 31.0 to 22.6.
MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1.25 / $10 for GPT-5-Codex.
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-Codex and MiniMax-M3 specifications
	GPT-5-Codex	MiniMax-M3
Provider	OpenAI	MiniMax
Noometry Index	37.9	43.8
Released	2025-09-15	2026-06-01
Weights	Proprietary	Open
Context window	400K	1M
Max output	128K	512K
Input $ / M tokens	$1.25	$0.30
Output $ / M tokens	$10	$1.20
Results tracked	3	41

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

Category by category

Coding Too close to call

GPT-5-Codex: 42.4 (#103), MiniMax-M3: 41.8 (#118)

Coding benchmarks
Benchmark	GPT-5-Codex	MiniMax-M3
FrontierCode	—	14.7%
LMArena WebDev	—	1482
SciCode	—	47.1%
WeirdML	54.5%	—
LMArena Coding	—	1469
ALE-Bench	—	640.02

Agentic & Tool Use GPT-5-Codex leads

GPT-5-Codex: 31.0 (#72), MiniMax-M3: 22.6 (#130)

Agentic & Tool Use benchmarks
Benchmark	GPT-5-Codex	MiniMax-M3
Terminal-Bench	44.3%	—
APEX-Agents	—	37.7%
OSWorld 2.0	—	4.6%
GBAEval	—	0.9%
Vending-Bench 2	—	2,158

Reasoning Too close to call

GPT-5-Codex: 30.9 (#83), MiniMax-M3: 30.1 (#87)

Reasoning benchmarks
Benchmark	GPT-5-Codex	MiniMax-M3
SimpleBench	—	45.8%
Kagi LLM Benchmark	70.3%	—
NYT Connections (extended)	—	65.1%
CritPt	—	3.7%
Chess Puzzles	—	14%
LMArena Hard Prompts	—	1447
Mystery Game Puzzles	—	8%
DTBench	—	78.9%
LMCA	—	33.7%
Surface Evolver Bench	—	55%
Epoch Capabilities Index	—	146.95
ForecastBench	—	61.4

Math Not comparable

GPT-5-Codex: —, MiniMax-M3: 40.0 (#95)

Math benchmarks
Benchmark	GPT-5-Codex	MiniMax-M3
OTIS Mock AIME 2024-2025	—	71.1%
ProofBench	—	18%
LMArena Math	—	1429

Knowledge Not comparable

GPT-5-Codex: —, MiniMax-M3: 58.4 (#35)

Knowledge benchmarks
Benchmark	GPT-5-Codex	MiniMax-M3
GPQA Diamond	—	90.9%
LMArena Expert	—	1461

Multimodal Not comparable

GPT-5-Codex: —, MiniMax-M3: 40.2 (#51)

Multimodal benchmarks
Benchmark	GPT-5-Codex	MiniMax-M3
LMArena Vision	—	1253
LMArena Document	—	1435

Multilingual Not comparable

GPT-5-Codex: —, MiniMax-M3: 53.0 (#75)

Multilingual benchmarks
Benchmark	GPT-5-Codex	MiniMax-M3
LMArena Non-English	—	1420
LMArena Chinese	—	1463
LMArena French	—	1447
LMArena German	—	1426
LMArena Japanese	—	1381
LMArena Korean	—	1372
LMArena Russian	—	1428
LMArena Spanish	—	1432

Instruction Following Not comparable

GPT-5-Codex: —, MiniMax-M3: 75.5 (#62)

Instruction Following benchmarks
Benchmark	GPT-5-Codex	MiniMax-M3
LMArena Instruction Following	—	1433

Long Context Not comparable

GPT-5-Codex: —, MiniMax-M3: 44.2 (#72)

Long Context benchmarks
Benchmark	GPT-5-Codex	MiniMax-M3
LMArena Longer Query	—	1445

Writing & Preference Not comparable

GPT-5-Codex: —, MiniMax-M3: 62.1 (#83)

Writing & Preference benchmarks
Benchmark	GPT-5-Codex	MiniMax-M3
LMArena Text	—	1433
LMArena Creative Writing	—	1404
EQ-Bench 4	—	1150
LMArena Multi-Turn	—	1442

Frequently asked questions

Is GPT-5-Codex better than MiniMax-M3?

MiniMax-M3 is the stronger model overall, scoring 43.8 to 37.9 on the Noometry Index.

Which is cheaper, GPT-5-Codex or MiniMax-M3?

MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; GPT-5-Codex lists at $1.25 and $10.

Is GPT-5-Codex or MiniMax-M3 better for coding?

They score almost the same on coding (42.4 vs 41.8); test both on your own repository before choosing.

Which has the bigger context window?

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

How many benchmarks do GPT-5-Codex and MiniMax-M3 share?

0 benchmarks have published results for both models. GPT-5-Codex has 3 scored results on Noometry and MiniMax-M3 has 41.