BenchLeader

MiniMax M3.1 Flash vs Solar Pro 4

Full profiles: MiniMax M3.1 Flash (MiniMax) and Solar Pro 4 (Upstage): every benchmark, price and rank.

Updated · Data from 7 sources

As of 16 Nov 2026, MiniMax M3.1 Flash and Solar Pro 4 are neck and neck on quality (54.3 vs 48.9 on the BenchLeader Index, inside the ±8.7 margin), and MiniMax M3.1 Flash is 2.0× cheaper at $0.262 vs $0.525 per 1M tokens blended. MiniMax M3.1 Flash leads in every category we measure both in. MiniMax M3.1 Flash streams ~2× faster.

Key facts (as of 16 Nov 2026)

  • MiniMax M3.1 Flash scores 54.3 on the BenchLeader Index and Solar Pro 4 scores 48.9 (BenchLeader, 16 Nov 2026).
  • MiniMax M3.1 Flash costs $0.262 per 1M tokens blended (list price, 16 Nov 2026).
  • Solar Pro 4 costs $0.525 per 1M tokens blended (list price, 16 Nov 2026).
  • MiniMax M3.1 Flash streams ~2× faster than Solar Pro 4 (Artificial Analysis, 7-day median, 16 Nov 2026).
  • Of the 23 benchmarks both models have, MiniMax M3.1 Flash leads 21 (BenchLeader, 16 Nov 2026).
  • On Arena WebDev, MiniMax M3.1 Flash is rated 1584 and Solar Pro 4 1369 (LMArena, as published by 16 Nov 2026).

Which to pick for…

The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.

Use casePickWhyConfidence
CodingMiniMax M3.1 Flash55 vs 40 category score; Arena WebDev 1584 vs 1369High
Agents & tool useMiniMax M3.1 Flash55 vs 40 category score; Arena Agent -2.7 vs -22.6High
ReasoningMiniMax M3.1 Flash50 vs 40 category score; HLE-Diamond (AA) 28.1% vs 4.7%High
KnowledgeEither46 vs 46 category score; AA-Omniscience v1.1 -6.4 vs 1.4Either
Long documentsMiniMax M3.1 Flash65 vs 60 category score; AA-LCR v1.1 79.7% vs 70.7%Medium
Chat quality (human preference)–Only Solar Pro 4 has an Arena rating (56 category score)Not comparable
Lowest costMiniMax M3.1 Flash$0.262 vs $0.525 per 1M blended; agentic coding session $0.011 vs $0.023–
Fastest first answerSolar Pro 428.2 s (Solar Pro 4) vs 43.3 s (MiniMax M3.1 Flash) to the first answer token–
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • MiniMax M3.1 Flash and Solar Pro 4 are neck and neck on quality (54.3 vs 48.9, within the ±8.7 margin).
  • MiniMax M3.1 Flash is stronger in agents & tools, coding, knowledge, long context, reasoning.
  • MiniMax M3.1 Flash is 2.0× cheaper ($0.262 vs $0.525 per 1M blended).
  • MiniMax M3.1 Flash streams 2.0× faster (151 vs 76 tokens per second).

At a glance

SpecMiniMax M3.1 FlashSolar Pro 4
DeveloperMiniMaxUpstage
Released19 Oct 20266 Aug 2026
Context window (tokens)1,000,000524,288
Compared atMiniMax M3.1 FlashSolar Pro 4
Open weightsYesNo
Price in / out / cached input per 1M$0.150 / $0.600 / $0.015$0.300 / $1.20 / $0.060

Category by category

Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.

CategoryMiniMax M3.1 FlashSolar Pro 4Leader
Reasoning50.140.3MiniMax M3.1 Flash
Coding55.440.4MiniMax M3.1 Flash
Agents & tools55.239.5MiniMax M3.1 Flash
Maths–58.9not comparable
Knowledge45.945.5level
Human preference–55.6not comparable
Multimodal61.5–not comparable
Long context64.559.8MiniMax M3.1 Flash

On one chart

Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.

2550 avg75ReasoningCodingAgents & toolsKnowledgeLong contextMiniMax M3.1 Flash, Reasoning: 50.1MiniMax M3.1 Flash, Coding: 55.4MiniMax M3.1 Flash, Agents & tools: 55.2MiniMax M3.1 Flash, Knowledge: 45.9MiniMax M3.1 Flash, Long context: 64.5Solar Pro 4, Reasoning: 40.3Solar Pro 4, Coding: 40.4Solar Pro 4, Agents & tools: 39.5Solar Pro 4, Knowledge: 45.5Solar Pro 4, Long context: 59.8

Not drawn, measured for fewer than two of these models: Maths, Instruction following, Multimodal, Human preference.

Model, click to add or removeIndex

Where sources disagree

Across the 23 benchmarks both have, MiniMax M3.1 Flash leads 21, Solar Pro 4 leads 2. Every overall index that rates both puts MiniMax M3.1 Flash ahead.

Overall indexMiniMax M3.1 FlashSolar Pro 4Leader
BenchLeader Index54.348.9neck and neck
AA Intelligence Index v5.0.129.114.2MiniMax M3.1 Flash

Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).

Price, speed and latency

List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.

MeasureMiniMax M3.1 FlashSolar Pro 4
Blended price per 1M tokens$0.262$0.525
Input / output per 1M$0.150 / $0.600$0.300 / $1.20
Cached input per 1M$0.015$0.060
Price per task: chat reply$0.0002$0.0005
Price per task: summarize a 30-page report$0.0022$0.0043
Price per task: code edit$0.0018$0.0036
Price per task: agentic coding session$0.011$0.023
Price per task: structured extraction$0.0004$0.0008
Agentic coding session, input mostly cached$0.0053$0.012
Cost per benchmark task (AA Index)$0.491$0.956
Output tokens per task (AA Index)138k311k
Of which reasoning103k263k
Time per task (AA Index)15 min69 min
Output speed151 tok/s76 tok/s
Time to first answer43.3 s28.2 s
Time to a complete answer, last measured 13 Nov 2026141.5 s72.8 s

Per token is not per task: an average task of Artificial Analysis' Intelligence Index cost $0.491 on MiniMax M3.1 Flash and $0.956 on Solar Pro 4, and Solar Pro 4 wrote 2.3× as many output tokens for the same work, which a per-token price hides.

Each model is compared at its best-ranked reasoning-effort setting. MiniMax M3.1 Flash scores 54.3 and takes 43 s to its first answer token. Solar Pro 4 scores 48.9 and takes 28 s to its first answer token. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.

Every benchmark

73 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.

MetricPublisherMiniMax M3.1 FlashSolar Pro 4
BenchLeader IndexBenchLeader54.348.9
Agents & tools scoreBenchLeader55.239.5
Coding scoreBenchLeader55.440.4
Knowledge scoreBenchLeader45.945.5
Long context scoreBenchLeader64.559.8
Multimodal scoreBenchLeader61.5–
Reasoning scoreBenchLeader50.140.3
Human preference scoreBenchLeader–55.6
Maths scoreBenchLeader–58.9
Blended price $/MBenchLeader$0.262$0.525
Output speedBenchLeader151 tok/s76 tok/s
Time to first answerBenchLeader43.3 s28.2 s
Context windowBenchLeader1,000,000 tokens524,288 tokens
Reasoning
Arena Hard PromptsArena (LMArena)–1409
LiveBench 2.0 ReasoningLiveBench82.9%†–
GPQA Diamond (AA)Artificial Analysis–89.1%
Humanity's Last Exam (AA)Artificial Analysis48.0%29.8%
HLE-Diamond (AA)Artificial Analysis28.1%4.7%
CritPtArtificial Analysis22.3%6.3%
CritPt v2 hard subset (AA)Artificial Analysis32.5%18.0%
Arena ExpertArena (LMArena)–1436
Coding
Arena CodingArena (LMArena)–1461
Arena WebDevArena (LMArena)15841369
LiveBench 2.0 CodingLiveBench68.8%†–
SciCode (AA)Artificial Analysis53.4%48.0%
Vibe Code Bench v1.1Vals AI73.9%†–
Vibe Code Bench 1-100 v1.1Vals AI19.8%†–
SWE-Bench Pro V2Scale AI SEAL96.6%†–
SWE-Bench Pro V2 HARDScale AI SEAL84.3%†–
Terminal-Bench 4.0 (AA)Artificial Analysis25.8%0.0%
Terminal-Bench 2.1 (AA)Artificial Analysis–57.3%
GameBench 2 by reasoning settingDuelLab GameBench 230.3†–
Design Arena WebsiteDesign Arena12771163
FrontierCode 1.1 (AA)Artificial Analysis38.6%–
FrontierCode 2.0 (AA)Artificial Analysis20.8%4.1%
Agents & tools
Arena AgentArena (LMArena)-2.7-22.6
LiveBench Long AgenticLiveBench25.7%†–
LiveBench BrowserLiveBench80.6%†–
Show all 73 benchmarks
MetricPublisherMiniMax M3.1 FlashSolar Pro 4
Agents & tools
HiL-BenchScale AI SEAL65.7%–
GDPval-AA v2.1, normalised scoreArtificial Analysis47.9%30.3%
GDPval-AA v2.1Artificial Analysis14651106
τ³-Banking (AA)Artificial Analysis–23.3%
Finance Agent v2.1Vals AI58.8%†–
Harvey's Legal Agent Benchmark v1.1Vals AI7.5%†–
Legal Research BenchVals AI34.1%†–
Tax Agent BenchVals AI32.1%†–
Terminal-Bench 4.0 (Vals)Vals AI25.3%†–
Arena Agent Task CompletionArena (LMArena)-0.7-29.9
AutomationBenchArtificial Analysis72.5%13.6%
GDP.pdf (AA)Artificial Analysis20.8%7.0%
AA-Briefcase v1.1Artificial Analysis14741093
GDPxGDPx by SemiAnalysis4.0%†–
Design Arena AgenticDesign Arena12521084
Terminal-Bench-Science 0.1 (AA)Artificial Analysis3.3%0.0%
MKA (AA)Artificial Analysis33.5%–
Maths
Arena MathsArena (LMArena)–1414
Knowledge
LiveBench 2.0 Data AnalysisLiveBench71.4%†–
LiveBench ResearchLiveBench76.7%†–
AA-Omniscience v1.1Artificial Analysis-6.41.4
PRBench FinanceScale AI SEAL45.6%–
PRBench LegalScale AI SEAL45.1%–
Excel Modeling Benchmark v1.1Vals AI67.8%†–
Access to Justice BenchmarkVals AI73.3%†–
AA-Omniscience v1.1: accuracyArtificial Analysis45.1%18.4%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis6.3%79.1%
Instruction following
Arena Instruction FollowingArena (LMArena)–1377
Human preference
Arena TextArena (LMArena)–1388
Arena Creative WritingArena (LMArena)–1312
Arena Multi-turnArena (LMArena)–1389
Arena Longer QueriesArena (LMArena)–1385
Multimodal
LiveBench DesignLiveBench71.2%†–
MMMU-ProArtificial Analysis79.1%–
SAGEVals AI85.3%†–
VIALS-AAHandshake AI29.8%–
Long context
AA-LCR v1.1Artificial Analysis79.7%70.7%
MLCRArtificial Analysis16.7%–
Composite
LiveBench 2.0LiveBench63.7%†–
AA Intelligence Index v5.0.1Artificial Analysis29.114.2
AA Intelligence Index v4.3.2Artificial Analysis42.726.6
AA Progress Index v1Artificial Analysis317.6280
Vals IndexVals AI53.8†–
Vals Finance IndexVals AI55.9%†–
Vals Router IndexVals AI53.8%–
Vals Legal IndexVals AI67.1%†–
Safety & honesty
FORTRESSScale AI SEAL52.1%–
Metadata
AA Openness IndexArtificial Analysis27.8–

Data as of 2026-11-16. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261111-7b598bb13de4 (https://benchmarks.duellab.org/releases/gb2-20261111-7b598bb13de4/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • MiniMax M3.1 Flash: BenchLeader Index 53.7 → 54.3.
  • Solar Pro 4: BenchLeader Index 49.7 → 48.9.
  • Solar Pro 4: 2 new results (AA Intelligence Index v5.0.1, FrontierCode 2.0 (AA)); 1 score revision.
  • MiniMax M3.1 Flash: BenchLeader Index 54.3 → 53.7.
  • MiniMax M3.1 Flash: 1 score revision.
  • MiniMax M3.1 Flash: 6 score revisions.
  • Solar Pro 4: 1 score revision.
  • MiniMax M3.1 Flash: BenchLeader Index 53.0 → 54.3.
  • MiniMax M3.1 Flash: 1 new result (HiL-Bench).
  • Solar Pro 4: BenchLeader Index 52.0 → 49.7.

Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs

MiniMax M3.1 Flash vs Solar Pro 4: questions

Is MiniMax M3.1 Flash better than Solar Pro 4?
MiniMax M3.1 Flash and Solar Pro 4 are neck and neck on quality (54.3 vs 48.9, within the ±8.7 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 16 Nov 2026, so check the category scores for your use.
MiniMax M3.1 Flash vs Solar Pro 4: which is cheaper, and will that change?
MiniMax M3.1 Flash is cheaper today: $0.262 against $0.525 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is MiniMax M3.1 Flash or Solar Pro 4 better for coding?
MiniMax M3.1 Flash scores higher in coding (55 vs 40 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1584 for MiniMax M3.1 Flash against 1369 for Solar Pro 4.
Which is faster, MiniMax M3.1 Flash or Solar Pro 4?
MiniMax M3.1 Flash streams ~2× faster (151 vs 76 output tokens per second, Artificial Analysis 7-day median).
Is MiniMax M3.1 Flash or Solar Pro 4 better for agents and tool use?
MiniMax M3.1 Flash scores higher in agentic tasks (55 vs 40 on the category index, where 50 is average). On Arena Agent, the top shared agents & tools benchmark, it is -2.7 for MiniMax M3.1 Flash against -22.6 for Solar Pro 4.
More questions (4)
Which is better for long documents?
MiniMax M3.1 Flash scores higher on long-context benchmarks (65 vs 60). MiniMax M3.1 Flash accepts more context: 1,000,000 against 524,288 tokens for Solar Pro 4.
Which has lower latency?
Solar Pro 4 answers first: 28.2 s against 43.3 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
Do independent benchmarks agree on MiniMax M3.1 Flash vs Solar Pro 4?
Across the 23 benchmarks both have, MiniMax M3.1 Flash leads 21, Solar Pro 4 leads 2. Every overall index that rates both puts MiniMax M3.1 Flash ahead.
When was MiniMax M3.1 Flash released?
MiniMax M3.1 Flash was released on 19 Oct 2026.