Model comparison

MiniMax-M2.5 vs Qwen3-Coder 480B-A35B Instruct

MiniMax-M2.5 and Qwen3-Coder 480B-A35B Instruct score almost the same on the Noometry Index (38.1 vs 37.7), so choose on price, context window or the category you care about most.

Last verified October 10, 2026. 22 shared benchmarks.

MiniMax-M2.5

MiniMax

38.1

Rank #181 Confirmed

Qwen3-Coder 480B-A35B Instruct

Alibaba (Qwen)

37.7

Rank #186 Confirmed

Summary

They share 22 benchmarks with published results for both. MiniMax-M2.5 scores higher in 3 categories and Qwen3-Coder 480B-A35B Instruct in 6 categories; 7 gaps are clear of the uncertainty.
The widest gap is in coding, where MiniMax-M2.5 leads 47.9 to 36.2.
The biggest single-benchmark swing is SWE-bench Verified (bash only): 75.8% for MiniMax-M2.5 and 55.4% for Qwen3-Coder 480B-A35B Instruct.
MiniMax-M2.5 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1.50 / $7.50 for Qwen3-Coder 480B-A35B Instruct.
Qwen3-Coder 480B-A35B Instruct accepts more context: 262K tokens versus 205K.

Side by side

MiniMax-M2.5 and Qwen3-Coder 480B-A35B Instruct specifications
	MiniMax-M2.5	Qwen3-Coder 480B-A35B Instruct
Provider	MiniMax	Alibaba (Qwen)
Noometry Index	38.1	37.7
Released	2026-02-12	2025-04
Weights	Open	Open
Context window	205K	262K
Max output	131K	66K
Input $ / M tokens	$0.30	$1.50
Output $ / M tokens	$1.20	$7.50
Results tracked	33	25

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

Category by category

Coding MiniMax-M2.5 leads

MiniMax-M2.5: 47.9 (#53), Qwen3-Coder 480B-A35B Instruct: 36.2 (#199)

Coding benchmarks
Benchmark	MiniMax-M2.5	Qwen3-Coder 480B-A35B Instruct
SWE-bench Verified (bash only)	75.8%	55.4%
LMArena WebDev	1386	1275
LMArena Coding	1380	1413
ALE-Bench	618.17	461.45
SWE-bench Multilingual	68.3%	—
GSO	—	4.9%
WeirdML	—	41.2%
AlgoTune	—	1.44

Agentic & Tool Use MiniMax-M2.5 leads

MiniMax-M2.5: 30.2 (#70), Qwen3-Coder 480B-A35B Instruct: 23.7 (#116)

Agentic & Tool Use benchmarks
Benchmark	MiniMax-M2.5	Qwen3-Coder 480B-A35B Instruct
Terminal-Bench	42.7%	27.2%
Vending-Bench 2	-23.16	—

Reasoning Qwen3-Coder 480B-A35B Instruct leads

MiniMax-M2.5: 17.6 (#281), Qwen3-Coder 480B-A35B Instruct: 24.7 (#141)

Reasoning benchmarks
Benchmark	MiniMax-M2.5	Qwen3-Coder 480B-A35B Instruct
Kagi LLM Benchmark	55.2%	49.5%
LMArena Hard Prompts	1372	1372
ARC-AGI-2	4.9%	—
NYT Connections (extended)	16.8%	—
ARC-AGI-1	63.7%	—
Epoch Capabilities Index	146.68	—

Math Qwen3-Coder 480B-A35B Instruct leads

MiniMax-M2.5: 25.8 (#242), Qwen3-Coder 480B-A35B Instruct: 34.9 (#151)

Math benchmarks
Benchmark	MiniMax-M2.5	Qwen3-Coder 480B-A35B Instruct
LMArena Math	1378	1364
ProofBench	4%	—

Knowledge MiniMax-M2.5 leads

MiniMax-M2.5: 38.6 (#132), Qwen3-Coder 480B-A35B Instruct: 36.4 (#159)

Knowledge benchmarks
Benchmark	MiniMax-M2.5	Qwen3-Coder 480B-A35B Instruct
LMArena Expert	1378	1337
Vectara Hallucination Rate	9.1%	—

Multilingual Too close to call

MiniMax-M2.5: 47.3 (#147), Qwen3-Coder 480B-A35B Instruct: 47.8 (#143)

Multilingual benchmarks
Benchmark	MiniMax-M2.5	Qwen3-Coder 480B-A35B Instruct
LMArena Non-English	1338	1345
LMArena Chinese	1392	1356
LMArena French	1363	1394
LMArena German	1361	1324
LMArena Japanese	1169	1309
LMArena Korean	1232	1307
LMArena Russian	1359	1367
LMArena Spanish	1354	1360

Instruction Following Too close to call

MiniMax-M2.5: 71.7 (#143), Qwen3-Coder 480B-A35B Instruct: 71.8 (#142)

Instruction Following benchmarks
Benchmark	MiniMax-M2.5	Qwen3-Coder 480B-A35B Instruct
LMArena Instruction Following	1353	1356

Long Context Qwen3-Coder 480B-A35B Instruct leads

MiniMax-M2.5: 37.4 (#211), Qwen3-Coder 480B-A35B Instruct: 42.0 (#126)

Long Context benchmarks
Benchmark	MiniMax-M2.5	Qwen3-Coder 480B-A35B Instruct
LMArena Longer Query	1367	1379
CL-bench	11.4%	—
CL-bench Life	6.3%	—

Writing & Preference Qwen3-Coder 480B-A35B Instruct leads

MiniMax-M2.5: 54.1 (#149), Qwen3-Coder 480B-A35B Instruct: 55.5 (#142)

Writing & Preference benchmarks
Benchmark	MiniMax-M2.5	Qwen3-Coder 480B-A35B Instruct
LMArena Text	1359	1356
LMArena Creative Writing	1331	1333
LMArena Multi-Turn	1364	1365
EQ-Bench Creative Writing	1361	—

Frequently asked questions

Is MiniMax-M2.5 better than Qwen3-Coder 480B-A35B Instruct?

MiniMax-M2.5 and Qwen3-Coder 480B-A35B Instruct score almost the same on the Noometry Index (38.1 vs 37.7), so choose on price, context window or the category you care about most.

Which is cheaper, MiniMax-M2.5 or Qwen3-Coder 480B-A35B Instruct?

MiniMax-M2.5 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-M2.5 or Qwen3-Coder 480B-A35B Instruct better for coding?

MiniMax-M2.5 scores higher on coding benchmarks: 47.9 versus 36.2 in the Noometry coding category.

Which has the bigger context window?

Qwen3-Coder 480B-A35B Instruct does, with 262K tokens against 205K.

How many benchmarks do MiniMax-M2.5 and Qwen3-Coder 480B-A35B Instruct share?

22 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.