Model comparison

DeepSeek-V3.2-Exp vs MiniMax M1

DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 40.3 on the Noometry Index.

Last verified October 12, 2026. 18 shared benchmarks.

DeepSeek-V3.2-Exp

DeepSeek

44.3

Rank #78 Confirmed

MiniMax M1

MiniMax

40.3

Rank #150 Confirmed

Summary

They share 18 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 7 categories and MiniMax M1 in 1 category; 8 gaps are clear of the uncertainty.
The widest gap is in knowledge, where DeepSeek-V3.2-Exp leads 51.7 to 36.4.
The biggest single-benchmark swing is Fiction.LiveBench: 83.3% for DeepSeek-V3.2-Exp and 69.4% for MiniMax M1.
DeepSeek-V3.2-Exp is cheaper at $0.26 / $0.38 per million input/output tokens, against $0.55 / $2.20 for MiniMax M1.
MiniMax M1 accepts more context: 1M tokens versus 164K.

Side by side

DeepSeek-V3.2-Exp and MiniMax M1 specifications
	DeepSeek-V3.2-Exp	MiniMax M1
Provider	DeepSeek	MiniMax
Noometry Index	44.3	40.3
Released	2025-09-29	2025-06-13
Weights	Open	Open
Context window	164K	1M
Max output	66K	40K
Input $ / M tokens	$0.26	$0.55
Output $ / M tokens	$0.38	$2.20
Results tracked	49	18

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

Category by category

Coding DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 46.5 (#65), MiniMax M1: 39.9 (#153)

Coding benchmarks
Benchmark	DeepSeek-V3.2-Exp	MiniMax M1
LMArena Coding	1454	1359
SWE-bench Verified (bash only)	70%	—
Aider Polyglot	74.2%	—
LMArena WebDev	1362	—
SWE-bench Multilingual	59%	—
SciCode	38.9%	—
WeirdML	39.5%	—

Agentic & Tool Use Not comparable

DeepSeek-V3.2-Exp: 32.7 (#59), MiniMax M1: —

Agentic & Tool Use benchmarks
Benchmark	DeepSeek-V3.2-Exp	MiniMax M1
Terminal-Bench	39.6%	—
APEX-Agents	21.3%	—
Berkeley Function Calling Leaderboard	56.7%	—
TheAgentCompany	42.9%	—
Vending-Bench 2	1,034	—

Reasoning MiniMax M1 leads

DeepSeek-V3.2-Exp: 22.1 (#208), MiniMax M1: 26.9 (#126)

Reasoning benchmarks
Benchmark	DeepSeek-V3.2-Exp	MiniMax M1
LMArena Hard Prompts	1434	1339
ARC-AGI-2	4%	—
Kagi LLM Benchmark	52.2%	—
NYT Connections (extended)	36.7%	—
ARC-AGI-1	57%	—
CritPt	2.9%	—
Chess Puzzles	14%	—
Thematic Generalization	65%	—
DTBench	87.7%	—
LMCA	29.1%	—
Epoch Capabilities Index	146.27	—

Math DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 41.7 (#87), MiniMax M1: 37.5 (#151)

Math benchmarks
Benchmark	DeepSeek-V3.2-Exp	MiniMax M1
LMArena Math	1435	1361
MathArena Final-Answer Competitions	57.7%	—
OTIS Mock AIME 2024-2025	87.8%	—
ProofBench	8%	—
FrontierMath (Feb 2025 set)	22.1%	—
FrontierMath Tier 4 (v1)	2.1%	—

Knowledge DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 51.7 (#66), MiniMax M1: 36.4 (#170)

Knowledge benchmarks
Benchmark	DeepSeek-V3.2-Exp	MiniMax M1
LMArena Expert	1436	1317
GPQA Diamond	83.4%	—
Vectara Hallucination Rate	5.3%	—

Multilingual DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 52.2 (#90), MiniMax M1: 45.8 (#163)

Multilingual benchmarks
Benchmark	DeepSeek-V3.2-Exp	MiniMax M1
LMArena Non-English	1409	1319
LMArena Chinese	1461	1360
LMArena French	1433	1370
LMArena German	1440	1350
LMArena Japanese	1374	1217
LMArena Korean	1371	1266
LMArena Russian	1424	1329
LMArena Spanish	1440	1353

Instruction Following DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 74.5 (#93), MiniMax M1: 69.3 (#174)

Instruction Following benchmarks
Benchmark	DeepSeek-V3.2-Exp	MiniMax M1
LMArena Instruction Following	1413	1312

Long Context DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 47.6 (#16), MiniMax M1: 41.4 (#141)

Long Context benchmarks
Benchmark	DeepSeek-V3.2-Exp	MiniMax M1
Fiction.LiveBench	83.3%	69.4%
LMArena Longer Query	1428	1326
CL-bench	13.2%	—
CL-bench Life	9.5%	—

Writing & Preference DeepSeek-V3.2-Exp leads

DeepSeek-V3.2-Exp: 62.4 (#77), MiniMax M1: 53.1 (#161)

Writing & Preference benchmarks
Benchmark	DeepSeek-V3.2-Exp	MiniMax M1
LMArena Text	1425	1343
LMArena Creative Writing	1403	1298
LMArena Multi-Turn	1427	1335
EQ-Bench Creative Writing	1515	—

Frequently asked questions

Is DeepSeek-V3.2-Exp better than MiniMax M1?

DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 40.3 on the Noometry Index.

Which is cheaper, DeepSeek-V3.2-Exp or MiniMax M1?

DeepSeek-V3.2-Exp is cheaper. It lists at $0.26 per million input tokens and $0.38 per million output tokens; MiniMax M1 lists at $0.55 and $2.20.

Is DeepSeek-V3.2-Exp or MiniMax M1 better for coding?

DeepSeek-V3.2-Exp scores higher on coding benchmarks: 46.5 versus 39.9 in the Noometry coding category.

Which has the bigger context window?

MiniMax M1 does, with 1M tokens against 164K.

How many benchmarks do DeepSeek-V3.2-Exp and MiniMax M1 share?

18 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 49 scored results on Noometry and MiniMax M1 has 18.