Model comparison

MiniMax-M3 vs Qwen2.5-Coder-32B

MiniMax-M3 is the stronger model overall, scoring 43.8 to 33.4 on the Noometry Index.

Last verified October 10, 2026. 13 shared benchmarks.

MiniMax-M3

MiniMax

43.8

Rank #85 Confirmed

Qwen2.5-Coder-32B

Alibaba (Qwen)

33.4

Rank #245 Confirmed

Summary

They share 13 benchmarks with published results for both. MiniMax-M3 scores higher in 8 categories and Qwen2.5-Coder-32B in 0 categories; 8 gaps are clear of the uncertainty.
The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 33.4.
MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.66 / $1 for Qwen2.5-Coder-32B.
MiniMax-M3 accepts more context: 1M tokens versus 33K.

Side by side

MiniMax-M3 and Qwen2.5-Coder-32B specifications
	MiniMax-M3	Qwen2.5-Coder-32B
Provider	MiniMax	Alibaba (Qwen)
Noometry Index	43.8	33.4
Released	2026-06-01	2024-09-18
Weights	Open	Open
Context window	1M	33K
Max output	512K	29K
Input $ / M tokens	$0.30	$0.66
Output $ / M tokens	$1.20	$1
Results tracked	41	31

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

Category by category

Coding MiniMax-M3 leads

MiniMax-M3: 41.8 (#118), Qwen2.5-Coder-32B: 22.6 (#333)

Coding benchmarks
Benchmark	MiniMax-M3	Qwen2.5-Coder-32B
LMArena Coding	1469	1276
FrontierCode	14.7%	—
SWE-bench Verified (bash only)	—	9%
Aider Polyglot	—	16.4%
LMArena WebDev	1482	—
SciCode	47.1%	—
BigCodeBench Instruct	—	49%
LiveBench Coding	—	56.9%
BigCodeBench Complete	—	58%
ALE-Bench	640.02	—
HumanEval+	—	87.2%
MBPP+	—	77%

Agentic & Tool Use Not comparable

MiniMax-M3: 22.6 (#130), Qwen2.5-Coder-32B: —

Agentic & Tool Use benchmarks
Benchmark	MiniMax-M3	Qwen2.5-Coder-32B
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), Qwen2.5-Coder-32B: 21.2 (#225)

Reasoning benchmarks
Benchmark	MiniMax-M3	Qwen2.5-Coder-32B
LMArena Hard Prompts	1447	1251
Epoch Capabilities Index	146.95	119.49
SimpleBench	45.8%	—
NYT Connections (extended)	65.1%	—
CritPt	3.7%	—
Chess Puzzles	14%	—
LiveBench Reasoning	—	42.1%
Mystery Game Puzzles	8%	—
DTBench	78.9%	—
LiveBench Data Analysis	—	49.9%
LMCA	33.7%	—
Surface Evolver Bench	55%	—
ForecastBench	61.4	—
HellaSwag	—	83%
LiveBench	—	46.2%
WinoGrande	—	80.8%

Math MiniMax-M3 leads

MiniMax-M3: 40.0 (#95), Qwen2.5-Coder-32B: 33.3 (#204)

Math benchmarks
Benchmark	MiniMax-M3	Qwen2.5-Coder-32B
LMArena Math	1429	1251
OTIS Mock AIME 2024-2025	71.1%	—
ProofBench	18%	—
LiveBench Math	—	46.6%
GSM8K	—	93%

Knowledge MiniMax-M3 leads

MiniMax-M3: 58.4 (#35), Qwen2.5-Coder-32B: 33.4 (#203)

Knowledge benchmarks
Benchmark	MiniMax-M3	Qwen2.5-Coder-32B
LMArena Expert	1461	1221
GPQA Diamond	90.9%	—
ARC (AI2) Challenge	—	70.5%
MMLU	—	79.1%

Multimodal Not comparable

MiniMax-M3: 40.2 (#51), Qwen2.5-Coder-32B: —

Multimodal benchmarks
Benchmark	MiniMax-M3	Qwen2.5-Coder-32B
LMArena Vision	1253	—
LMArena Document	1435	—

Multilingual MiniMax-M3 leads

MiniMax-M3: 53.0 (#75), Qwen2.5-Coder-32B: 37.8 (#235)

Multilingual benchmarks
Benchmark	MiniMax-M3	Qwen2.5-Coder-32B
LMArena Non-English	1420	1205
LMArena Chinese	1463	1222
LMArena Russian	1428	1228
LMArena French	1447	—
LMArena German	1426	—
LMArena Japanese	1381	—
LMArena Korean	1372	—
LMArena Spanish	1432	—

Instruction Following MiniMax-M3 leads

MiniMax-M3: 75.5 (#62), Qwen2.5-Coder-32B: 61.4 (#245)

Instruction Following benchmarks
Benchmark	MiniMax-M3	Qwen2.5-Coder-32B
LMArena Instruction Following	1433	1223
LiveBench Instruction Following	—	58.7%

Long Context MiniMax-M3 leads

MiniMax-M3: 44.2 (#72), Qwen2.5-Coder-32B: 38.0 (#208)

Long Context benchmarks
Benchmark	MiniMax-M3	Qwen2.5-Coder-32B
LMArena Longer Query	1445	1251

Writing & Preference MiniMax-M3 leads

MiniMax-M3: 62.1 (#83), Qwen2.5-Coder-32B: 41.6 (#240)

Writing & Preference benchmarks
Benchmark	MiniMax-M3	Qwen2.5-Coder-32B
LMArena Text	1433	1230
LMArena Creative Writing	1404	1174
LMArena Multi-Turn	1442	1222
EQ-Bench 4	1150	—
LiveBench Language	—	23.3%

Frequently asked questions

Is MiniMax-M3 better than Qwen2.5-Coder-32B?

MiniMax-M3 is the stronger model overall, scoring 43.8 to 33.4 on the Noometry Index.

Which is cheaper, MiniMax-M3 or Qwen2.5-Coder-32B?

MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Qwen2.5-Coder-32B lists at $0.66 and $1.

Is MiniMax-M3 or Qwen2.5-Coder-32B better for coding?

MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 22.6 in the Noometry coding category.

Which has the bigger context window?

MiniMax-M3 does, with 1M tokens against 33K.

How many benchmarks do MiniMax-M3 and Qwen2.5-Coder-32B share?

13 benchmarks have published results for both models. MiniMax-M3 has 41 scored results on Noometry and Qwen2.5-Coder-32B has 31.