Model comparison

MiniMax-M2.5 vs Qwen3-Next 80B-A3B Instruct

Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 43.0 to 38.3 on the Noometry Index. MiniMax-M2.5 costs 1.7× less per token, which makes it the better buy when Qwen3-Next 80B-A3B Instruct's lead doesn't matter for your workload.

Last verified October 12, 2026. 19 shared benchmarks.

MiniMax-M2.5

MiniMax

38.3

Rank #188 Confirmed

Qwen3-Next 80B-A3B Instruct

Alibaba (Qwen)

43.0

Rank #102 Confirmed

Summary

They share 19 benchmarks with published results for both. MiniMax-M2.5 scores higher in 3 categories and Qwen3-Next 80B-A3B Instruct in 5 categories; 6 gaps are clear of the uncertainty.
The widest gap is in reasoning, where Qwen3-Next 80B-A3B Instruct leads 31.1 to 17.5.
The biggest single-benchmark swing is Kagi LLM Benchmark: 55.2% for MiniMax-M2.5 and 66.7% for Qwen3-Next 80B-A3B Instruct.
MiniMax-M2.5 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.50 / $2 for Qwen3-Next 80B-A3B Instruct.
MiniMax-M2.5 accepts more context: 205K tokens versus 131K.

Side by side

MiniMax-M2.5 and Qwen3-Next 80B-A3B Instruct specifications
	MiniMax-M2.5	Qwen3-Next 80B-A3B Instruct
Provider	MiniMax	Alibaba (Qwen)
Noometry Index	38.3	43.0
Released	2026-02-12	2025-09
Weights	Open	Open
Context window	205K	131K
Max output	131K	33K
Input $ / M tokens	$0.30	$0.50
Output $ / M tokens	$1.20	$2
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: 48.1 (#58), Qwen3-Next 80B-A3B Instruct: 42.5 (#98)

Coding benchmarks
Benchmark	MiniMax-M2.5	Qwen3-Next 80B-A3B Instruct
LMArena Coding	1381	1440
SWE-bench Verified (bash only)	75.8%	—
LMArena WebDev	1387	—
SWE-bench Multilingual	68.3%	—
ALE-Bench	618.17	—

Agentic & Tool Use Not comparable

MiniMax-M2.5: 30.4 (#77), Qwen3-Next 80B-A3B Instruct: —

Agentic & Tool Use benchmarks
Benchmark	MiniMax-M2.5	Qwen3-Next 80B-A3B Instruct
Terminal-Bench	42.7%	—
Vending-Bench 2	-23.16	—

Reasoning Qwen3-Next 80B-A3B Instruct leads

MiniMax-M2.5: 17.5 (#292), Qwen3-Next 80B-A3B Instruct: 31.1 (#81)

Reasoning benchmarks
Benchmark	MiniMax-M2.5	Qwen3-Next 80B-A3B Instruct
Kagi LLM Benchmark	55.2%	66.7%
LMArena Hard Prompts	1372	1428
ARC-AGI-2	4.9%	—
NYT Connections (extended)	16.8%	—
ARC-AGI-1	63.7%	—
Epoch Capabilities Index	146.68	—

Math Qwen3-Next 80B-A3B Instruct leads

MiniMax-M2.5: 26.9 (#253), Qwen3-Next 80B-A3B Instruct: 38.8 (#126)

Math benchmarks
Benchmark	MiniMax-M2.5	Qwen3-Next 80B-A3B Instruct
LMArena Math	1378	1440
ProofBench	4%	—
Omni-MATH	—	46.7%

Knowledge Qwen3-Next 80B-A3B Instruct leads

MiniMax-M2.5: 39.2 (#135), Qwen3-Next 80B-A3B Instruct: 41.8 (#106)

Knowledge benchmarks
Benchmark	MiniMax-M2.5	Qwen3-Next 80B-A3B Instruct
Vectara Hallucination Rate	9.1%	9.3%
LMArena Expert	1379	1417
MMLU-Pro	—	78.6%
GPQA (HELM)	—	63%

Multilingual Qwen3-Next 80B-A3B Instruct leads

MiniMax-M2.5: 47.1 (#152), Qwen3-Next 80B-A3B Instruct: 52.1 (#93)

Multilingual benchmarks
Benchmark	MiniMax-M2.5	Qwen3-Next 80B-A3B Instruct
LMArena Non-English	1338	1407
LMArena Chinese	1393	1460
LMArena French	1362	1413
LMArena German	1362	1417
LMArena Japanese	1171	1395
LMArena Korean	1232	1364
LMArena Russian	1358	1404
LMArena Spanish	1354	1435

Instruction Following Too close to call

MiniMax-M2.5: 71.5 (#148), Qwen3-Next 80B-A3B Instruct: 70.8 (#159)

Instruction Following benchmarks
Benchmark	MiniMax-M2.5	Qwen3-Next 80B-A3B Instruct
LMArena Instruction Following	1353	1389
IFEval	—	81%

Long Context Too close to call

MiniMax-M2.5: 37.5 (#216), Qwen3-Next 80B-A3B Instruct: 37.0 (#223)

Long Context benchmarks
Benchmark	MiniMax-M2.5	Qwen3-Next 80B-A3B Instruct
LMArena Longer Query	1366	1403
Fiction.LiveBench	—	55.6%
CL-bench	11.4%	—
CL-bench Life	6.3%	—

Writing & Preference Qwen3-Next 80B-A3B Instruct leads

MiniMax-M2.5: 53.9 (#153), Qwen3-Next 80B-A3B Instruct: 58.0 (#121)

Writing & Preference benchmarks
Benchmark	MiniMax-M2.5	Qwen3-Next 80B-A3B Instruct
LMArena Text	1359	1417
LMArena Creative Writing	1331	1334
LMArena Multi-Turn	1364	1416
EQ-Bench Creative Writing	1361	—
WildBench	—	80.7%

Frequently asked questions

Is MiniMax-M2.5 better than Qwen3-Next 80B-A3B Instruct?

Which is cheaper, MiniMax-M2.5 or Qwen3-Next 80B-A3B Instruct?

MiniMax-M2.5 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Qwen3-Next 80B-A3B Instruct lists at $0.50 and $2.

Is MiniMax-M2.5 or Qwen3-Next 80B-A3B Instruct better for coding?

MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 42.5 in the Noometry coding category.

Which has the bigger context window?

MiniMax-M2.5 does, with 205K tokens against 131K.

How many benchmarks do MiniMax-M2.5 and Qwen3-Next 80B-A3B Instruct share?

19 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and Qwen3-Next 80B-A3B Instruct has 25.