Model comparison

MiniMax-M2 vs Solar Pro4

Solar Pro4 is the stronger model overall, scoring 42.1 to 37.4 on the Noometry Index.

Last verified . 16 shared benchmarks.

MiniMax-M2 MiniMax

37.4

Rank #204 Confirmed

Solar Pro4 Upstage

42.1

Rank #121 Confirmed

Summary

  • They share 16 benchmarks with published results for both. MiniMax-M2 scores higher in 0 categories and Solar Pro4 in 8 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Solar Pro4 leads 28.5 to 19.4.
  • Both cost about the same: $0.30 input and $1.20 output per million tokens.
  • Solar Pro4 accepts more context: 524K tokens versus 205K.
  • MiniMax-M2 has downloadable open weights; the other is API-only.

Side by side

MiniMax-M2 and Solar Pro4 specifications
MiniMax-M2Solar Pro4
ProviderMiniMaxUpstage
Noometry Index37.442.1
Released2025-10-272026-08-06
WeightsOpenProprietary
Context window205K524K
Max output131K131K
Input $ / M tokens$0.30$0.30
Output $ / M tokens$1.20$1.20
Results tracked2118

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

Category by category

Coding Too close to call

MiniMax-M2: 39.3 (#159), Solar Pro4: 40.1 (#149)

Coding benchmarks
BenchmarkMiniMax-M2Solar Pro4
LMArena WebDev12971371
LMArena Coding13701437
SWE-bench Verified (bash only)61%—

Agentic & Tool Use Not comparable

MiniMax-M2: 25.1 (#109), Solar Pro4: —

Agentic & Tool Use benchmarks
BenchmarkMiniMax-M2Solar Pro4
Terminal-Bench30%—
Vending-Bench 2160.6—

Reasoning Solar Pro4 leads

MiniMax-M2: 19.4 (#258), Solar Pro4: 28.5 (#104)

Reasoning benchmarks
BenchmarkMiniMax-M2Solar Pro4
LMArena Hard Prompts13571399
Kagi LLM Benchmark57.8%—
NYT Connections (extended)14.8%—

Math Solar Pro4 leads

MiniMax-M2: 37.3 (#160), Solar Pro4: 38.8 (#128)

Math benchmarks
BenchmarkMiniMax-M2Solar Pro4
LMArena Math13521416

Knowledge Solar Pro4 leads

MiniMax-M2: 37.0 (#163), Solar Pro4: 39.8 (#129)

Knowledge benchmarks
BenchmarkMiniMax-M2Solar Pro4
LMArena Expert13371427

Multilingual Solar Pro4 leads

MiniMax-M2: 45.3 (#171), Solar Pro4: 48.7 (#139)

Multilingual benchmarks
BenchmarkMiniMax-M2Solar Pro4
LMArena Non-English13131361
LMArena Chinese13661415
LMArena French13351397
LMArena German13551364
LMArena Russian13311360
LMArena Spanish13261401
LMArena Japanese—1309
LMArena Korean—1382

Instruction Following Solar Pro4 leads

MiniMax-M2: 70.2 (#166), Solar Pro4: 72.7 (#132)

Instruction Following benchmarks
BenchmarkMiniMax-M2Solar Pro4
LMArena Instruction Following13281377

Long Context Solar Pro4 leads

MiniMax-M2: 40.5 (#153), Solar Pro4: 42.1 (#130)

Long Context benchmarks
BenchmarkMiniMax-M2Solar Pro4
LMArena Longer Query13311381

Writing & Preference Solar Pro4 leads

MiniMax-M2: 53.0 (#162), Solar Pro4: 56.5 (#138)

Writing & Preference benchmarks
BenchmarkMiniMax-M2Solar Pro4
LMArena Text13401386
LMArena Creative Writing12861316
LMArena Multi-Turn13611385

Frequently asked questions

Is MiniMax-M2 better than Solar Pro4?

Solar Pro4 is the stronger model overall, scoring 42.1 to 37.4 on the Noometry Index.

Which is cheaper, MiniMax-M2 or Solar Pro4?

Solar Pro4 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; MiniMax-M2 lists at $0.30 and $1.20.

Is MiniMax-M2 or Solar Pro4 better for coding?

They score almost the same on coding (39.3 vs 40.1); test both on your own repository before choosing.

Which has the bigger context window?

Solar Pro4 does, with 524K tokens against 205K.

How many benchmarks do MiniMax-M2 and Solar Pro4 share?

16 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and Solar Pro4 has 18.

Related comparisons

Go deeper