Model comparison

MiniMax-M3 vs Qwen3-Coder 480B-A35B Instruct

MiniMax-M3 is the stronger model overall, scoring 43.8 to 38.1 on the Noometry Index.

Last verified October 10, 2026. 19 shared benchmarks.

MiniMax-M3

MiniMax

43.8

Rank #85 Confirmed

Qwen3-Coder 480B-A35B Instruct

Alibaba (Qwen)

38.1

Rank #190 Confirmed

Summary

They share 19 benchmarks with published results for both. MiniMax-M3 scores higher in 8 categories and Qwen3-Coder 480B-A35B Instruct in 1 category; 9 gaps are clear of the uncertainty.
The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 37.0.
MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1.50 / $7.50 for Qwen3-Coder 480B-A35B Instruct.
MiniMax-M3 accepts more context: 1M tokens versus 262K.

Side by side

MiniMax-M3 and Qwen3-Coder 480B-A35B Instruct specifications
	MiniMax-M3	Qwen3-Coder 480B-A35B Instruct
Provider	MiniMax	Alibaba (Qwen)
Noometry Index	43.8	38.1
Released	2026-06-01	2025-04
Weights	Open	Open
Context window	1M	262K
Max output	512K	66K
Input $ / M tokens	$0.30	$1.50
Output $ / M tokens	$1.20	$7.50
Results tracked	41	25

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

Category by category

Coding MiniMax-M3 leads

MiniMax-M3: 41.8 (#118), Qwen3-Coder 480B-A35B Instruct: 35.5 (#223)

Coding benchmarks
Benchmark	MiniMax-M3	Qwen3-Coder 480B-A35B Instruct
LMArena WebDev	1482	1275
LMArena Coding	1469	1412
ALE-Bench	640.02	461.45
FrontierCode	14.7%	—
SWE-bench Verified (bash only)	—	55.4%
SciCode	47.1%	—
GSO	—	4.9%
WeirdML	—	41.2%
AlgoTune	—	1.44

Agentic & Tool Use Qwen3-Coder 480B-A35B Instruct leads

MiniMax-M3: 22.6 (#130), Qwen3-Coder 480B-A35B Instruct: 23.9 (#123)

Agentic & Tool Use benchmarks
Benchmark	MiniMax-M3	Qwen3-Coder 480B-A35B Instruct
Terminal-Bench	—	27.2%
APEX-Agents	37.7%	—
OSWorld 2.0	4.6%	—
GBAEval	0.9%	—
Vending-Bench 2	2,158	—

Reasoning MiniMax-M3 leads

MiniMax-M3: 30.1 (#87), Qwen3-Coder 480B-A35B Instruct: 25.5 (#149)

Reasoning benchmarks
Benchmark	MiniMax-M3	Qwen3-Coder 480B-A35B Instruct
LMArena Hard Prompts	1447	1372
SimpleBench	45.8%	—
Kagi LLM Benchmark	—	49.5%
NYT Connections (extended)	65.1%	—
CritPt	3.7%	—
Chess Puzzles	14%	—
Mystery Game Puzzles	8%	—
DTBench	78.9%	—
LMCA	33.7%	—
Surface Evolver Bench	55%	—
Epoch Capabilities Index	146.95	—
ForecastBench	61.4	—

Math MiniMax-M3 leads

MiniMax-M3: 40.0 (#95), Qwen3-Coder 480B-A35B Instruct: 37.6 (#150)

Math benchmarks
Benchmark	MiniMax-M3	Qwen3-Coder 480B-A35B Instruct
LMArena Math	1429	1365
OTIS Mock AIME 2024-2025	71.1%	—
ProofBench	18%	—

Knowledge MiniMax-M3 leads

MiniMax-M3: 58.4 (#35), Qwen3-Coder 480B-A35B Instruct: 37.0 (#162)

Knowledge benchmarks
Benchmark	MiniMax-M3	Qwen3-Coder 480B-A35B Instruct
LMArena Expert	1461	1338
GPQA Diamond	90.9%	—

Multimodal Not comparable

MiniMax-M3: 40.2 (#51), Qwen3-Coder 480B-A35B Instruct: —

Multimodal benchmarks
Benchmark	MiniMax-M3	Qwen3-Coder 480B-A35B Instruct
LMArena Vision	1253	—
LMArena Document	1435	—

Multilingual MiniMax-M3 leads

MiniMax-M3: 53.0 (#75), Qwen3-Coder 480B-A35B Instruct: 47.7 (#148)

Multilingual benchmarks
Benchmark	MiniMax-M3	Qwen3-Coder 480B-A35B Instruct
LMArena Non-English	1420	1346
LMArena Chinese	1463	1357
LMArena French	1447	1398
LMArena German	1426	1325
LMArena Japanese	1381	1310
LMArena Korean	1372	1305
LMArena Russian	1428	1366
LMArena Spanish	1432	1360

Instruction Following MiniMax-M3 leads

MiniMax-M3: 75.5 (#62), Qwen3-Coder 480B-A35B Instruct: 71.6 (#147)

Instruction Following benchmarks
Benchmark	MiniMax-M3	Qwen3-Coder 480B-A35B Instruct
LMArena Instruction Following	1433	1355

Long Context MiniMax-M3 leads

MiniMax-M3: 44.2 (#72), Qwen3-Coder 480B-A35B Instruct: 42.0 (#131)

Long Context benchmarks
Benchmark	MiniMax-M3	Qwen3-Coder 480B-A35B Instruct
LMArena Longer Query	1445	1378

Writing & Preference MiniMax-M3 leads

MiniMax-M3: 62.1 (#83), Qwen3-Coder 480B-A35B Instruct: 55.3 (#147)

Writing & Preference benchmarks
Benchmark	MiniMax-M3	Qwen3-Coder 480B-A35B Instruct
LMArena Text	1433	1357
LMArena Creative Writing	1404	1333
LMArena Multi-Turn	1442	1365
EQ-Bench 4	1150	—

Frequently asked questions

Is MiniMax-M3 better than Qwen3-Coder 480B-A35B Instruct?

MiniMax-M3 is the stronger model overall, scoring 43.8 to 38.1 on the Noometry Index.

Which is cheaper, MiniMax-M3 or Qwen3-Coder 480B-A35B Instruct?

MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Qwen3-Coder 480B-A35B Instruct lists at $1.50 and $7.50.

Is MiniMax-M3 or Qwen3-Coder 480B-A35B Instruct better for coding?

MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 35.5 in the Noometry coding category.

Which has the bigger context window?

MiniMax-M3 does, with 1M tokens against 262K.

How many benchmarks do MiniMax-M3 and Qwen3-Coder 480B-A35B Instruct share?

19 benchmarks have published results for both models. MiniMax-M3 has 41 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.