Model comparison

MiniMax-M2 vs Qwen3 14B

MiniMax-M2 is the stronger model overall, scoring 37.4 to 35.5 on the Noometry Index.

Last verified October 10, 2026. 1 shared benchmarks.

MiniMax-M2

MiniMax

37.4

Rank #204 Confirmed

Qwen3 14B

Alibaba (Qwen)

35.5

Rank #225 Confirmed

Summary

They share 1 benchmark with published results for both. MiniMax-M2 scores higher in 3 categories and Qwen3 14B in 3 categories; 5 gaps are clear of the uncertainty.
The widest gap is in agentic & tool use, where Qwen3 14B leads 29.6 to 25.1.
The biggest single-benchmark swing is Kagi LLM Benchmark: 57.8% for MiniMax-M2 and 49.1% for Qwen3 14B.
MiniMax-M2 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.35 / $1.40 for Qwen3 14B.
MiniMax-M2 accepts more context: 205K tokens versus 131K.

Side by side

MiniMax-M2 and Qwen3 14B specifications
	MiniMax-M2	Qwen3 14B
Provider	MiniMax	Alibaba (Qwen)
Noometry Index	37.4	35.5
Released	2025-10-27	2025-04
Weights	Open	Open
Context window	205K	131K
Max output	131K	8K
Input $ / M tokens	$0.30	$0.35
Output $ / M tokens	$1.20	$1.40
Results tracked	21	12

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

Category by category

Coding MiniMax-M2 leads

MiniMax-M2: 39.3 (#159), Qwen3 14B: 37.3 (#195)

Coding benchmarks
Benchmark	MiniMax-M2	Qwen3 14B
SWE-bench Verified (bash only)	61%	—
LMArena WebDev	1297	—
SciCode	—	31.6%
LMArena Coding	1370	—

Agentic & Tool Use Qwen3 14B leads

MiniMax-M2: 25.1 (#109), Qwen3 14B: 29.6 (#83)

Agentic & Tool Use benchmarks
Benchmark	MiniMax-M2	Qwen3 14B
Terminal-Bench	30%	—
Berkeley Function Calling Leaderboard	—	41%
Vending-Bench 2	160.6	—

Reasoning Too close to call

MiniMax-M2: 19.4 (#258), Qwen3 14B: 18.5 (#280)

Reasoning benchmarks
Benchmark	MiniMax-M2	Qwen3 14B
Kagi LLM Benchmark	57.8%	49.1%
NYT Connections (extended)	14.8%	—
CritPt	—	0%
Chess Puzzles	—	4%
LMArena Hard Prompts	1357	—
DTBench	—	64%
LMCA	—	18.2%
Epoch Capabilities Index	—	138.23

Math Qwen3 14B leads

MiniMax-M2: 37.3 (#160), Qwen3 14B: 38.6 (#133)

Math benchmarks
Benchmark	MiniMax-M2	Qwen3 14B
OTIS Mock AIME 2024-2025	—	66.4%
LMArena Math	1352	—

Knowledge Qwen3 14B leads

MiniMax-M2: 37.0 (#163), Qwen3 14B: 39.3 (#134)

Knowledge benchmarks
Benchmark	MiniMax-M2	Qwen3 14B
GPQA Diamond	—	63.8%
Vectara Hallucination Rate	—	5.4%
LMArena Expert	1337	—

Multilingual Not comparable

MiniMax-M2: 45.3 (#171), Qwen3 14B: —

Multilingual benchmarks
Benchmark	MiniMax-M2	Qwen3 14B
LMArena Non-English	1313	—
LMArena Chinese	1366	—
LMArena French	1335	—
LMArena German	1355	—
LMArena Russian	1331	—
LMArena Spanish	1326	—

Instruction Following Not comparable

MiniMax-M2: 70.2 (#166), Qwen3 14B: —

Instruction Following benchmarks
Benchmark	MiniMax-M2	Qwen3 14B
LMArena Instruction Following	1328	—

Long Context MiniMax-M2 leads

MiniMax-M2: 40.5 (#153), Qwen3 14B: 38.1 (#204)

Long Context benchmarks
Benchmark	MiniMax-M2	Qwen3 14B
Fiction.LiveBench	—	62.5%
LMArena Longer Query	1331	—

Writing & Preference Not comparable

MiniMax-M2: 53.0 (#162), Qwen3 14B: —

Writing & Preference benchmarks
Benchmark	MiniMax-M2	Qwen3 14B
LMArena Text	1340	—
LMArena Creative Writing	1286	—
LMArena Multi-Turn	1361	—

Frequently asked questions

Is MiniMax-M2 better than Qwen3 14B?

MiniMax-M2 is the stronger model overall, scoring 37.4 to 35.5 on the Noometry Index.

Which is cheaper, MiniMax-M2 or Qwen3 14B?

MiniMax-M2 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Qwen3 14B lists at $0.35 and $1.40.

Is MiniMax-M2 or Qwen3 14B better for coding?

MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 37.3 in the Noometry coding category.

Which has the bigger context window?

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

How many benchmarks do MiniMax-M2 and Qwen3 14B share?

1 benchmark has published results for both models. MiniMax-M2 has 21 scored results on Noometry and Qwen3 14B has 12.