LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

MiniMax M2 vs Solar Pro 4

Updated October 21, 2026. 38 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace MiniMax M2 Replace Solar Pro 4
MiniMax M2MiniMax
Coding
45.3
Overall
18.6
Output $/M
$1.02
1
Solar Pro 4Upstage
Coding
24.4
Overall
28.2
Output $/M
$0.60
37
vs boards won of 38 shared

Decision reading

Pick MiniMax M2 for coding: it scores 45.3 on the Vibe Coding Index against 24.4 for Solar Pro 4.

Pick Solar Pro 4 when output tokens cost 1.7x less, or when the context window is larger, 524K against 205K tokens.

Model AMiniMax M2MiniMax45.3/1002 independent benchmarks$0.702 per solved taskModel BSolar Pro 4Upstage24.4/1001 independent benchmarkNo cost per solved task
Shared results
38
MiniMax M2 only
11
Solar Pro 4 only
7
Like-for-like categories
7 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
MiniMax M2 45.3 from 2 benchmarks, Solar Pro 4 24.4 from 1 benchmark.
Widest category
Reasoning, 11.6 points apart on average over 5 shared benchmarks.
Widest single gap
Humanity's Last Exam (Artificial Analysis run): MiniMax M2 13.7% against Solar Pro 4 29.8%, 16.1 points apart on a 0 to 100 scale.
Output price
MiniMax M2 $1.02 against Solar Pro 4 $0.60 per million output tokens, 1.7x apart.
Context window
MiniMax M2 takes 205K tokens, Solar Pro 4 524K.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryMiniMax M2BarsSolar Pro 4Ties
Coding04
Intelligence01
Reasoning05
Math02
Knowledge04
Web design06
General115
All shared boards137
CodingLike-for-likeFour of these boards feed the Vibe Coding Index04
Coding benchmarks for MiniMax M2 and Solar Pro 4
BenchmarkMiniMax M2Solar Pro 4Leader
SWE-bench Verified61.0%Not measuredOnly MiniMax M2 measured
LMArena WebDev12971371Solar Pro 4
AA Coding IndexNot measured52.7Only Solar Pro 4 measured
LiveCodeBench (Artificial Analysis run)82.6%Not measuredOnly MiniMax M2 measured
SciCodeNot measured48.0%Only Solar Pro 4 measured
Terminal-Bench Hard (Artificial Analysis run)25.8%Not measuredOnly MiniMax M2 measured
Terminal-Bench30.0%Not measuredOnly MiniMax M2 measured
ALE-BenchNot measured179.3Only Solar Pro 4 measured
LMArena Text: coding13711438Solar Pro 4
LMArena Text: software and IT13731431Solar Pro 4
LMArena WebDev: ReactNot measured1363Only Solar Pro 4 measured
LMArena WebDev: HTML13061371Solar Pro 4
Neither model has a result on the other 26 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for MiniMax M2 and Solar Pro 4
BenchmarkMiniMax M2Solar Pro 4Leader
AA Intelligence Index18.628.2Solar Pro 4
Neither model has a result on the other 1 board here
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
Agentic work benchmarks for MiniMax M2 and Solar Pro 4
BenchmarkMiniMax M2Solar Pro 4Leader
Design Arena: agents building web appsNot measured1105Only Solar Pro 4 measured
τ²-Bench Telecom86.8%Not measuredOnly MiniMax M2 measured
Vending-Bench 2$161Not measuredOnly MiniMax M2 measured
Neither model has a result on the other 36 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
Reasoning benchmarks for MiniMax M2 and Solar Pro 4
BenchmarkMiniMax M2Solar Pro 4Leader
GPQA Diamond (Artificial Analysis run)77.7%89.1%Solar Pro 4
Humanity's Last Exam (Artificial Analysis run)13.7%29.8%Solar Pro 4
LMArena Text: hard prompts13571400Solar Pro 4
LMArena Text: expert13381428Solar Pro 4
LMArena Text: hard prompts in English13761427Solar Pro 4
Neither model has a result on the other 16 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for MiniMax M2 and Solar Pro 4
BenchmarkMiniMax M2Solar Pro 4Leader
AA Math Index78.3Not measuredOnly MiniMax M2 measured
AIME 2025 (Artificial Analysis run)78.3%Not measuredOnly MiniMax M2 measured
LMArena Text: math13511421Solar Pro 4
LMArena Text: mathematical work13681427Solar Pro 4
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for MiniMax M2 and Solar Pro 4
BenchmarkMiniMax M2Solar Pro 4Leader
MMLU Pro (Artificial Analysis run)82.0%Not measuredOnly MiniMax M2 measured
LMArena Text: science13481404Solar Pro 4
LMArena Text: medicine and healthcare13671374Solar Pro 4
LMArena Text: legal and government13491383Solar Pro 4
LMArena Text: business and finance13361381Solar Pro 4
Neither model has a result on the other 12 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index06
Web design benchmarks for MiniMax M2 and Solar Pro 4
BenchmarkMiniMax M2Solar Pro 4Leader
Design Arena: websites11441176Solar Pro 4
Design Arena: UI components11361150Solar Pro 4
Design Arena: game dev11191170Solar Pro 4
Design Arena: data viz11401177Solar Pro 4
Design Arena: 3D10981178Solar Pro 4
Design Arena: all code categories11351182Solar Pro 4
Design Arena: SVG1098Not measuredOnly MiniMax M2 measured
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index115
General benchmarks for MiniMax M2 and Solar Pro 4
BenchmarkMiniMax M2Solar Pro 4Leader
IFBench72.3%Not measuredOnly MiniMax M2 measured
Long context reasoning (AA-LCR)64.3%70.7%Solar Pro 4
LMArena Text13401388Solar Pro 4
LMArena Text: instruction following13291375Solar Pro 4
LMArena Text: creative writing12861317Solar Pro 4
LMArena Text: English13641414Solar Pro 4
LMArena Text: non-English13131363Solar Pro 4
LMArena Text: Chinese13661422Solar Pro 4
LMArena Text: German13571358Solar Pro 4
LMArena Text: JapaneseNot measured1320Only Solar Pro 4 measured
LMArena Text: KoreanNot measured1383Only Solar Pro 4 measured
LMArena Text: French13361400Solar Pro 4
LMArena Text: Spanish13261409Solar Pro 4
LMArena Text: Russian13301357Solar Pro 4
LMArena Text: Polish13121304MiniMax M2
LMArena Text: multi-turn13611385Solar Pro 4
LMArena Text: longer queries13311382Solar Pro 4
LMArena Text: writing and language12951344Solar Pro 4
LMArena Text: entertainment and media12981332Solar Pro 4
Neither model has a result on the other 27 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for MiniMax M2 and Solar Pro 4
BenchmarkMiniMax M2Solar Pro 4Leader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

MiniMax M2$0.0008Fits in one request
Solar Pro 4$0.0004Fits in one request

Solar Pro 4 costs less

Repository review

50K input + 3K output tokens

MiniMax M2$0.016Fits in one request
Solar Pro 4$0.0093Fits in one request

Solar Pro 4 costs less

Agent loop

200K input + 10K output tokens

MiniMax M2$0.061Exceeds the context window
Solar Pro 4$0.036Fits in one request

Solar Pro 4 costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of MiniMax M2 and Solar Pro 4
SpecificationMiniMax M2Upstage Solar Pro 4
MakerMiniMaxUpstage
WeightsOpen weightsNo public weights listed
ReleasedOctober 23, 2025August 10, 2026
Context window205K524K
Input $/Mtok$0.255$0.15
Output $/Mtok$1.02$0.60
Coding index45.324.4
Independent measurements behind it21
Cost per solved task$0.702Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is MiniMax M2 better than Solar Pro 4 for coding?

Pick MiniMax M2 for coding: it scores 45.3 on the Vibe Coding Index against 24.4 for Solar Pro 4. Pick Solar Pro 4 when output tokens cost 1.7x less, or when the context window is larger, 524K against 205K tokens.

Which is cheaper, MiniMax M2 or Solar Pro 4?

MiniMax M2 costs $0.255 per million input tokens and $1.02 per million output tokens; Solar Pro 4 costs $0.15 and $0.60. Cost per solved task is known for MiniMax M2 only.

Which has the bigger context window, MiniMax M2 or Solar Pro 4?

Solar Pro 4, with 524K tokens against 205K.

How many benchmarks is the MiniMax M2 vs Solar Pro 4 comparison based on?

38 benchmarks have a result for both models as of October 21, 2026. MiniMax M2's coding index rests on 2 independent benchmarks and Solar Pro 4's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next