Model comparison

MiniMax-M2 vs Nova 2 Lite

Nova 2 Lite is the stronger model overall, scoring 39.0 to 36.9 on the Noometry Index. MiniMax-M2 costs 1.6× less per token, which makes it the better buy when Nova 2 Lite's lead doesn't matter for your workload.

Last verified . 15 shared benchmarks.

MiniMax-M2 MiniMax

36.9

Rank #201 Confirmed

Nova 2 Lite Amazon

39.0

Rank #161 Confirmed

Summary

  • They share 15 benchmarks with published results for both. MiniMax-M2 scores higher in 1 category and Nova 2 Lite in 8 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Nova 2 Lite leads 26.4 to 18.6.
  • MiniMax-M2 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.30 / $2.50 for Nova 2 Lite.
  • Nova 2 Lite accepts more context: 1M tokens versus 205K.
  • MiniMax-M2 has downloadable open weights; the other is API-only.

Side by side

MiniMax-M2 and Nova 2 Lite specifications
MiniMax-M2Nova 2 Lite
ProviderMiniMaxAmazon
Noometry Index36.939.0
Released2025-10-272025-12-01
WeightsOpenProprietary
Context window205K1M
Max output131K64K
Input $ / M tokens$0.30$0.30
Output $ / M tokens$1.20$2.50
Results tracked2119

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

Category by category

Coding Nova 2 Lite leads

MiniMax-M2: 39.1 (#151), Nova 2 Lite: 40.1 (#131)

Coding benchmarks
BenchmarkMiniMax-M2Nova 2 Lite
LMArena Coding13701386
SWE-bench Verified (bash only)61%—
LMArena WebDev1297—

Agentic & Tool Use MiniMax-M2 leads

MiniMax-M2: 24.9 (#102), Nova 2 Lite: 23.9 (#114)

Agentic & Tool Use benchmarks
BenchmarkMiniMax-M2Nova 2 Lite
Terminal-Bench30%—
Berkeley Function Calling Leaderboard—27.1%
Vending-Bench 2160.6—

Reasoning Nova 2 Lite leads

MiniMax-M2: 18.6 (#256), Nova 2 Lite: 26.4 (#120)

Reasoning benchmarks
BenchmarkMiniMax-M2Nova 2 Lite
LMArena Hard Prompts13571364
Kagi LLM Benchmark57.8%—
NYT Connections (extended)14.8%—

Math Too close to call

MiniMax-M2: 34.6 (#158), Nova 2 Lite: 34.8 (#154)

Math benchmarks
BenchmarkMiniMax-M2Nova 2 Lite
LMArena Math13501359

Knowledge Nova 2 Lite leads

MiniMax-M2: 36.3 (#160), Nova 2 Lite: 42.5 (#88)

Knowledge benchmarks
BenchmarkMiniMax-M2Nova 2 Lite
LMArena Expert13361360
Vectara Hallucination Rate—5.1%

Multilingual Nova 2 Lite leads

MiniMax-M2: 45.6 (#165), Nova 2 Lite: 47.3 (#148)

Multilingual benchmarks
BenchmarkMiniMax-M2Nova 2 Lite
LMArena Non-English13141337
LMArena Chinese13671364
LMArena French13361381
LMArena German13661343
LMArena Russian13321343
LMArena Spanish13261372
LMArena Japanese—1273
LMArena Korean—1284

Instruction Following Too close to call

MiniMax-M2: 70.4 (#160), Nova 2 Lite: 70.7 (#156)

Instruction Following benchmarks
BenchmarkMiniMax-M2Nova 2 Lite
LMArena Instruction Following13291335

Long Context Too close to call

MiniMax-M2: 40.5 (#148), Nova 2 Lite: 40.6 (#145)

Long Context benchmarks
BenchmarkMiniMax-M2Nova 2 Lite
LMArena Longer Query13321335

Writing & Preference Too close to call

MiniMax-M2: 53.3 (#157), Nova 2 Lite: 54.1 (#150)

Writing & Preference benchmarks
BenchmarkMiniMax-M2Nova 2 Lite
LMArena Text13401362
LMArena Creative Writing12881291
LMArena Multi-Turn13621338

Frequently asked questions

Is MiniMax-M2 better than Nova 2 Lite?

Nova 2 Lite is the stronger model overall, scoring 39.0 to 36.9 on the Noometry Index. MiniMax-M2 costs 1.6× less per token, which makes it the better buy when Nova 2 Lite's lead doesn't matter for your workload.

Which is cheaper, MiniMax-M2 or Nova 2 Lite?

MiniMax-M2 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Nova 2 Lite lists at $0.30 and $2.50.

Is MiniMax-M2 or Nova 2 Lite better for coding?

Nova 2 Lite scores higher on coding benchmarks: 40.1 versus 39.1 in the Noometry coding category.

Which has the bigger context window?

Nova 2 Lite does, with 1M tokens against 205K.

How many benchmarks do MiniMax-M2 and Nova 2 Lite share?

15 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and Nova 2 Lite has 19.

Related comparisons

Go deeper