Model comparison

MiniMax-M2.5 vs Qwen2.5-Coder-32B

MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 33.4 on the Noometry Index.

Last verified October 10, 2026. 14 shared benchmarks.

MiniMax-M2.5

MiniMax

38.3

Rank #188 Confirmed

Qwen2.5-Coder-32B

Alibaba (Qwen)

33.4

Rank #245 Confirmed

Summary

They share 14 benchmarks with published results for both. MiniMax-M2.5 scores higher in 5 categories and Qwen2.5-Coder-32B in 3 categories; 7 gaps are clear of the uncertainty.
The widest gap is in coding, where MiniMax-M2.5 leads 48.1 to 22.6.
The biggest single-benchmark swing is SWE-bench Verified (bash only): 75.8% for MiniMax-M2.5 and 9% for Qwen2.5-Coder-32B.
MiniMax-M2.5 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.66 / $1 for Qwen2.5-Coder-32B.
MiniMax-M2.5 accepts more context: 205K tokens versus 33K.

Side by side

MiniMax-M2.5 and Qwen2.5-Coder-32B specifications
	MiniMax-M2.5	Qwen2.5-Coder-32B
Provider	MiniMax	Alibaba (Qwen)
Noometry Index	38.3	33.4
Released	2026-02-12	2024-09-18
Weights	Open	Open
Context window	205K	33K
Max output	131K	29K
Input $ / M tokens	$0.30	$0.66
Output $ / M tokens	$1.20	$1
Results tracked	33	31

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

Category by category

Coding MiniMax-M2.5 leads

MiniMax-M2.5: 48.1 (#58), Qwen2.5-Coder-32B: 22.6 (#333)

Coding benchmarks
Benchmark	MiniMax-M2.5	Qwen2.5-Coder-32B
SWE-bench Verified (bash only)	75.8%	9%
LMArena Coding	1381	1276
Aider Polyglot	—	16.4%
LMArena WebDev	1387	—
SWE-bench Multilingual	68.3%	—
BigCodeBench Instruct	—	49%
LiveBench Coding	—	56.9%
BigCodeBench Complete	—	58%
ALE-Bench	618.17	—
HumanEval+	—	87.2%
MBPP+	—	77%

Agentic & Tool Use Not comparable

MiniMax-M2.5: 30.4 (#77), Qwen2.5-Coder-32B: —

Agentic & Tool Use benchmarks
Benchmark	MiniMax-M2.5	Qwen2.5-Coder-32B
Terminal-Bench	42.7%	—
Vending-Bench 2	-23.16	—

Reasoning Qwen2.5-Coder-32B leads

MiniMax-M2.5: 17.5 (#292), Qwen2.5-Coder-32B: 21.2 (#225)

Reasoning benchmarks
Benchmark	MiniMax-M2.5	Qwen2.5-Coder-32B
LMArena Hard Prompts	1372	1251
Epoch Capabilities Index	146.68	119.49
ARC-AGI-2	4.9%	—
Kagi LLM Benchmark	55.2%	—
NYT Connections (extended)	16.8%	—
ARC-AGI-1	63.7%	—
LiveBench Reasoning	—	42.1%
LiveBench Data Analysis	—	49.9%
HellaSwag	—	83%
LiveBench	—	46.2%
WinoGrande	—	80.8%

Math Qwen2.5-Coder-32B leads

MiniMax-M2.5: 26.9 (#253), Qwen2.5-Coder-32B: 33.3 (#204)

Math benchmarks
Benchmark	MiniMax-M2.5	Qwen2.5-Coder-32B
LMArena Math	1378	1251
ProofBench	4%	—
LiveBench Math	—	46.6%
GSM8K	—	93%

Knowledge MiniMax-M2.5 leads

MiniMax-M2.5: 39.2 (#135), Qwen2.5-Coder-32B: 33.4 (#203)

Knowledge benchmarks
Benchmark	MiniMax-M2.5	Qwen2.5-Coder-32B
LMArena Expert	1379	1221
Vectara Hallucination Rate	9.1%	—
ARC (AI2) Challenge	—	70.5%
MMLU	—	79.1%

Multilingual MiniMax-M2.5 leads

MiniMax-M2.5: 47.1 (#152), Qwen2.5-Coder-32B: 37.8 (#235)

Multilingual benchmarks
Benchmark	MiniMax-M2.5	Qwen2.5-Coder-32B
LMArena Non-English	1338	1205
LMArena Chinese	1393	1222
LMArena Russian	1358	1228
LMArena French	1362	—
LMArena German	1362	—
LMArena Japanese	1171	—
LMArena Korean	1232	—
LMArena Spanish	1354	—

Instruction Following MiniMax-M2.5 leads

MiniMax-M2.5: 71.5 (#148), Qwen2.5-Coder-32B: 61.4 (#245)

Instruction Following benchmarks
Benchmark	MiniMax-M2.5	Qwen2.5-Coder-32B
LMArena Instruction Following	1353	1223
LiveBench Instruction Following	—	58.7%

Long Context Too close to call

MiniMax-M2.5: 37.5 (#216), Qwen2.5-Coder-32B: 38.0 (#208)

Long Context benchmarks
Benchmark	MiniMax-M2.5	Qwen2.5-Coder-32B
LMArena Longer Query	1366	1251
CL-bench	11.4%	—
CL-bench Life	6.3%	—

Writing & Preference MiniMax-M2.5 leads

MiniMax-M2.5: 53.9 (#153), Qwen2.5-Coder-32B: 41.6 (#240)

Writing & Preference benchmarks
Benchmark	MiniMax-M2.5	Qwen2.5-Coder-32B
LMArena Text	1359	1230
LMArena Creative Writing	1331	1174
LMArena Multi-Turn	1364	1222
EQ-Bench Creative Writing	1361	—
LiveBench Language	—	23.3%

Frequently asked questions

Is MiniMax-M2.5 better than Qwen2.5-Coder-32B?

MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 33.4 on the Noometry Index.

Which is cheaper, MiniMax-M2.5 or Qwen2.5-Coder-32B?

MiniMax-M2.5 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-M2.5 or Qwen2.5-Coder-32B better for coding?

MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 22.6 in the Noometry coding category.

Which has the bigger context window?

MiniMax-M2.5 does, with 205K tokens against 33K.

How many benchmarks do MiniMax-M2.5 and Qwen2.5-Coder-32B share?

14 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and Qwen2.5-Coder-32B has 31.