Model comparison

MiniMax-M2 vs Qwen3.5 397B-A17B

Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 37.4 on the Noometry Index. MiniMax-M2 costs 2.6× less per token, which makes it the better buy when Qwen3.5 397B-A17B's lead doesn't matter for your workload.

Last verified October 12, 2026. 18 shared benchmarks.

MiniMax-M2

MiniMax

37.4

Rank #204 Confirmed

Qwen3.5 397B-A17B

Alibaba (Qwen)

46.0

Rank #67 Confirmed

Summary

They share 18 benchmarks with published results for both. MiniMax-M2 scores higher in 0 categories and Qwen3.5 397B-A17B in 9 categories; 9 gaps are clear of the uncertainty.
The widest gap is in knowledge, where Qwen3.5 397B-A17B leads 53.3 to 37.0.
The biggest single-benchmark swing is NYT Connections (extended): 14.8% for MiniMax-M2 and 58.9% for Qwen3.5 397B-A17B.
MiniMax-M2 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.60 / $3.60 for Qwen3.5 397B-A17B.
Qwen3.5 397B-A17B accepts more context: 262K tokens versus 205K.

Side by side

MiniMax-M2 and Qwen3.5 397B-A17B specifications
	MiniMax-M2	Qwen3.5 397B-A17B
Provider	MiniMax	Alibaba (Qwen)
Noometry Index	37.4	46.0
Released	2025-10-27	2026-02-01
Weights	Open	Open
Context window	205K	262K
Max output	131K	66K
Input $ / M tokens	$0.30	$0.60
Output $ / M tokens	$1.20	$3.60
Results tracked	21	36

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

Category by category

Coding Qwen3.5 397B-A17B leads

MiniMax-M2: 39.3 (#159), Qwen3.5 397B-A17B: 42.0 (#114)

Coding benchmarks
Benchmark	MiniMax-M2	Qwen3.5 397B-A17B
LMArena WebDev	1297	1400
LMArena Coding	1370	1465
SWE-bench Verified (bash only)	61%	—

Agentic & Tool Use Qwen3.5 397B-A17B leads

MiniMax-M2: 25.1 (#109), Qwen3.5 397B-A17B: 33.3 (#53)

Agentic & Tool Use benchmarks
Benchmark	MiniMax-M2	Qwen3.5 397B-A17B
Terminal-Bench	30%	—
APEX-Agents	—	24.9%
τ²-bench Airline	—	81.5%
τ²-bench Banking	—	9.8%
τ²-bench Retail	—	84.4%
τ²-bench Telecom	—	97.8%
Vending-Bench 2	160.6	—

Reasoning Qwen3.5 397B-A17B leads

MiniMax-M2: 19.4 (#258), Qwen3.5 397B-A17B: 34.5 (#70)

Reasoning benchmarks
Benchmark	MiniMax-M2	Qwen3.5 397B-A17B
Kagi LLM Benchmark	57.8%	73.7%
NYT Connections (extended)	14.8%	58.9%
LMArena Hard Prompts	1357	1448
Chess Puzzles	—	13%
Thematic Generalization	—	65.1%
Mystery Game Puzzles	—	18%
DTBench	—	87.5%
LMCA	—	37.9%
Epoch Capabilities Index	—	146.65

Math Qwen3.5 397B-A17B leads

MiniMax-M2: 37.3 (#160), Qwen3.5 397B-A17B: 46.1 (#73)

Math benchmarks
Benchmark	MiniMax-M2	Qwen3.5 397B-A17B
LMArena Math	1352	1454
FrontierMath (Tiers 1-3)	—	31.2%
OTIS Mock AIME 2024-2025	—	88.9%

Knowledge Qwen3.5 397B-A17B leads

MiniMax-M2: 37.0 (#163), Qwen3.5 397B-A17B: 53.3 (#58)

Knowledge benchmarks
Benchmark	MiniMax-M2	Qwen3.5 397B-A17B
LMArena Expert	1337	1462
GPQA Diamond	—	86.4%

Multimodal Not comparable

MiniMax-M2: —, Qwen3.5 397B-A17B: 40.7 (#44)

Multimodal benchmarks
Benchmark	MiniMax-M2	Qwen3.5 397B-A17B
LMArena Vision	—	1263

Multilingual Qwen3.5 397B-A17B leads

MiniMax-M2: 45.3 (#171), Qwen3.5 397B-A17B: 53.7 (#59)

Multilingual benchmarks
Benchmark	MiniMax-M2	Qwen3.5 397B-A17B
LMArena Non-English	1313	1430
LMArena Chinese	1366	1500
LMArena French	1335	1461
LMArena German	1355	1447
LMArena Russian	1331	1429
LMArena Spanish	1326	1441
LMArena Japanese	—	1426
LMArena Korean	—	1384

Instruction Following Qwen3.5 397B-A17B leads

MiniMax-M2: 70.2 (#166), Qwen3.5 397B-A17B: 75.0 (#77)

Instruction Following benchmarks
Benchmark	MiniMax-M2	Qwen3.5 397B-A17B
LMArena Instruction Following	1328	1424

Long Context Qwen3.5 397B-A17B leads

MiniMax-M2: 40.5 (#153), Qwen3.5 397B-A17B: 44.1 (#74)

Long Context benchmarks
Benchmark	MiniMax-M2	Qwen3.5 397B-A17B
LMArena Longer Query	1331	1442

Writing & Preference Qwen3.5 397B-A17B leads

MiniMax-M2: 53.0 (#162), Qwen3.5 397B-A17B: 62.3 (#79)

Writing & Preference benchmarks
Benchmark	MiniMax-M2	Qwen3.5 397B-A17B
LMArena Text	1340	1438
LMArena Creative Writing	1286	1401
LMArena Multi-Turn	1361	1446
EQ-Bench Creative Writing	—	1478

Frequently asked questions

Is MiniMax-M2 better than Qwen3.5 397B-A17B?

Which is cheaper, MiniMax-M2 or Qwen3.5 397B-A17B?

MiniMax-M2 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Qwen3.5 397B-A17B lists at $0.60 and $3.60.

Is MiniMax-M2 or Qwen3.5 397B-A17B better for coding?

Qwen3.5 397B-A17B scores higher on coding benchmarks: 42.0 versus 39.3 in the Noometry coding category.

Which has the bigger context window?

Qwen3.5 397B-A17B does, with 262K tokens against 205K.

How many benchmarks do MiniMax-M2 and Qwen3.5 397B-A17B share?

18 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and Qwen3.5 397B-A17B has 36.