Enter opens the highlighted result. Esc closes.

Mercury 2.5 vs MiniMax M3

MiniMax M3 leads Mercury 2.5 on coding, 39.2 to 1.6 on the Vibe Coding Index, and Mercury 2.5 costs 8.0x less per output token ($0.15 vs $1.20 per million). Updated October 22, 2026; 20 benchmarks have a result for both.

Replace Mercury 2.5 Replace MiniMax M3
Mercury 2.5Inception
Coding
1.6
Overall
No data
Output $/M
$0.15
0
MiniMax M3MiniMax
Coding
39.2
Overall
51.7
Output $/M
$1.20
20
vs boards won of 20 shared

Mercury 2.5 or MiniMax M3: which to pick

Pick MiniMax M3 for coding: it scores 39.2 on the Vibe Coding Index against 1.6 for Mercury 2.5.

Pick Mercury 2.5 for output tokens 8.0x cheaper ($0.15 vs $1.20 per million).

Model AMercury 2.5Inception1.6/1002 independent benchmarksNo cost per solved taskModel BMiniMax M3MiniMax39.2/1006 independent benchmarks$0.56 per solved task
Shared results
20
Mercury 2.5 only
2
MiniMax M3 only
97
Like-for-like categories
7 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

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
Mercury 2.5 1.6 from 2 benchmarks, MiniMax M3 39.2 from 6 benchmarks.
Widest category
Agentic work, 28.0 points apart on average over 4 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): Mercury 2.5 3.7% against MiniMax M3 47.6%, 43.9 points apart on a 0 to 100 scale.
Output price
Mercury 2.5 $0.15 against MiniMax M3 $1.20 per million output tokens, 8.0x apart.
Context window
Mercury 2.5 takes 260K tokens, MiniMax M3 1.05M.

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
CategoryMercury 2.5BarsMiniMax M3Ties
Coding08
Intelligence01
Agentic work04
Reasoning01
Math01
Knowledge02
General03
All shared boards020
CodingLike-for-likeSix of these boards feed the Vibe Coding Index08
Coding benchmarks for Mercury 2.5 and MiniMax M3
BenchmarkMercury 2.5MiniMax M3Leader
LiveBench codingNot measured70.9%Only MiniMax M3 measured
LMArena WebDevNot measured1482Only MiniMax M3 measured
AA Coding IndexNot measured58.6Only MiniMax M3 measured
LiveCodeBench (Vals AI)Not measured82.2%Only MiniMax M3 measured
SWE-bench Verified (Vals AI)Not measured75.0%Only MiniMax M3 measured
Terminal-Bench 4 (Vals AI)0.0%1.0%MiniMax M3
Vibe Code Bench (Vals AI)3.7%47.6%MiniMax M3
Code migration (Vals AI)4.5%19.9%MiniMax M3
IOI (Vals AI)2.4%Not measuredOnly Mercury 2.5 measured
Terminal-Bench 2.1 (Vals AI)34.5%53.6%MiniMax M3
SWE-bench Multimodal (Vals AI)Not measured33.3%Only MiniMax M3 measured
Vibe Code Bench 1-100 (Vals AI)Not measured9.2%Only MiniMax M3 measured
SkillsBench (Vals AI)18.1%51.5%MiniMax M3
CyberBench (Vals AI)45.5%65.0%MiniMax M3
SciCode38.5%47.1%MiniMax M3
Terminal-Bench Hard (Artificial Analysis run)Not measured42.4%Only MiniMax M3 measured
FrontierCodeNot measured14.7%Only MiniMax M3 measured
ALE-Bench301.6640.0MiniMax M3
LMArena Text: codingNot measured1470Only MiniMax M3 measured
LMArena Text: software and ITNot measured1466Only MiniMax M3 measured
LMArena WebDev: ReactNot measured1478Only MiniMax M3 measured
LMArena WebDev: HTMLNot measured1455Only MiniMax M3 measured
LMArena WebDev: from an imageNot measured1470Only MiniMax M3 measured
Neither model has a result on the other 20 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Mercury 2.5 and MiniMax M3
BenchmarkMercury 2.5MiniMax M3Leader
AA Intelligence Index12.329.2MiniMax M3
Epoch Capabilities IndexNot measured146.9Only MiniMax M3 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index04
Agentic work benchmarks for Mercury 2.5 and MiniMax M3
BenchmarkMercury 2.5MiniMax M3Leader
AA Agentic IndexNot measured29.5Only MiniMax M3 measured
Design Arena: agents building web appsNot measured1200Only MiniMax M3 measured
Design Arena: agents building full-stack appsNot measured1197Only MiniMax M3 measured
Design Arena: agents building mobile appsNot measured1169Only MiniMax M3 measured
Design Arena: agents building Android appsNot measured1158Only MiniMax M3 measured
Design Arena: agents building gamesNot measured1159Only MiniMax M3 measured
Design Arena: HTML slidesNot measured1120Only MiniMax M3 measured
Design Arena: PowerPoint slidesNot measured1178Only MiniMax M3 measured
Design Arena: spreadsheetsNot measured1042Only MiniMax M3 measured
LiveBench researchNot measured68.0%Only MiniMax M3 measured
LiveBench browserNot measured8.0%Only MiniMax M3 measured
LiveBench long agenticNot measured12.4%Only MiniMax M3 measured
Finance Agent (Vals AI)18.9%48.3%MiniMax M3
Tax Agent Bench (Vals AI)2.5%20.6%MiniMax M3
Legal Research Bench (Vals AI)4.3%29.8%MiniMax M3
Excel Modeling Benchmark (Vals AI)8.8%47.8%MiniMax M3
Terminal-Bench-Science (Vals AI)0.0%Not measuredOnly Mercury 2.5 measured
τ²-Bench TelecomNot measured88.9%Only MiniMax M3 measured
APEX-AgentsNot measured37.7%Only MiniMax M3 measured
OSWorld 2.0Not measured4.6%Only MiniMax M3 measured
Vending-Bench 2Not measured$2,158Only MiniMax M3 measured
Neither model has a result on the other 21 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index01
Reasoning benchmarks for Mercury 2.5 and MiniMax M3
BenchmarkMercury 2.5MiniMax M3Leader
GPQA DiamondNot measured92.7%Only MiniMax M3 measured
LiveBench reasoningNot measured74.5%Only MiniMax M3 measured
MMMU Pro (Vals AI)Not measured81.2%Only MiniMax M3 measured
GPQA Diamond (Artificial Analysis run)Not measured92.9%Only MiniMax M3 measured
Humanity's Last Exam (Artificial Analysis run)11.8%39.0%MiniMax M3
GPQA Diamond (Epoch AI run)Not measured90.9%Only MiniMax M3 measured
SimpleBenchNot measured45.8%Only MiniMax M3 measured
Chess puzzlesNot measured13.0%Only MiniMax M3 measured
Mystery game puzzlesNot measured8.0%Only MiniMax M3 measured
LMArena Text: hard promptsNot measured1447Only MiniMax M3 measured
LMArena Text: expertNot measured1461Only MiniMax M3 measured
LMArena Text: hard prompts in EnglishNot measured1455Only MiniMax M3 measured
LMArena Vision: diagramsNot measured1266Only MiniMax M3 measured
LMArena Vision: homeworkNot measured1268Only MiniMax M3 measured
Neither model has a result on the other 9 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index01
Math benchmarks for Mercury 2.5 and MiniMax M3
BenchmarkMercury 2.5MiniMax M3Leader
OTIS Mock AIMENot measured71.1%Only MiniMax M3 measured
ProofBench3.0%18.0%MiniMax M3
LMArena Text: mathNot measured1429Only MiniMax M3 measured
LMArena Text: mathematical workNot measured1448Only MiniMax M3 measured
Neither model has a result on the other 10 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index02
Knowledge benchmarks for Mercury 2.5 and MiniMax M3
BenchmarkMercury 2.5MiniMax M3Leader
MMLU ProNot measured84.2%Only MiniMax M3 measured
LegalBench (Vals AI)83.1%85.4%MiniMax M3
CorpFin (Vals AI)Not measured68.1%Only MiniMax M3 measured
TaxEval (Vals AI)Not measured72.7%Only MiniMax M3 measured
MortgageTax (Vals AI)Not measured68.4%Only MiniMax M3 measured
MedCode (Vals AI)31.3%46.3%MiniMax M3
LMArena Text: scienceNot measured1452Only MiniMax M3 measured
LMArena Text: medicine and healthcareNot measured1441Only MiniMax M3 measured
LMArena Text: legal and governmentNot measured1437Only MiniMax M3 measured
LMArena Text: business and financeNot measured1434Only MiniMax M3 measured
Neither model has a result on the other 10 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Web design benchmarks for Mercury 2.5 and MiniMax M3
BenchmarkMercury 2.5MiniMax M3Leader
Design Arena: websitesNot measured1257Only MiniMax M3 measured
Design Arena: UI componentsNot measured1243Only MiniMax M3 measured
Design Arena: game devNot measured1210Only MiniMax M3 measured
Design Arena: data vizNot measured1236Only MiniMax M3 measured
Design Arena: 3DNot measured1208Only MiniMax M3 measured
Design Arena: all code categoriesNot measured1246Only MiniMax M3 measured
Design Arena: SVGNot measured1160Only MiniMax M3 measured
Design Arena: ASCII artNot measured1161Only MiniMax M3 measured
LiveBench designNot measured66.2%Only MiniMax M3 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index03
General benchmarks for Mercury 2.5 and MiniMax M3
BenchmarkMercury 2.5MiniMax M3Leader
LiveBench data analysisNot measured76.2%Only MiniMax M3 measured
Public Benefits Bench (Vals AI)45.3%64.1%MiniMax M3
SAGE (Vals AI)Not measured50.6%Only MiniMax M3 measured
MedScribe (Vals AI)55.1%87.3%MiniMax M3
Vals Multimodal IndexNot measured60.0%Only MiniMax M3 measured
IFBenchNot measured82.9%Only MiniMax M3 measured
Long context reasoning (AA-LCR)71.7%83.0%MiniMax M3
DTBenchNot measured78.9%Only MiniMax M3 measured
LMCANot measured33.7%Only MiniMax M3 measured
Surface Evolver BenchNot measured55.0%Only MiniMax M3 measured
LMArena TextNot measured1433Only MiniMax M3 measured
LMArena Text: instruction followingNot measured1433Only MiniMax M3 measured
LMArena Text: creative writingNot measured1404Only MiniMax M3 measured
LMArena VisionNot measured1251Only MiniMax M3 measured
LMArena Text: EnglishNot measured1443Only MiniMax M3 measured
LMArena Text: non-EnglishNot measured1420Only MiniMax M3 measured
LMArena Text: ChineseNot measured1466Only MiniMax M3 measured
LMArena Text: GermanNot measured1428Only MiniMax M3 measured
LMArena Text: JapaneseNot measured1380Only MiniMax M3 measured
LMArena Text: KoreanNot measured1373Only MiniMax M3 measured
LMArena Text: FrenchNot measured1444Only MiniMax M3 measured
LMArena Text: SpanishNot measured1433Only MiniMax M3 measured
LMArena Text: RussianNot measured1426Only MiniMax M3 measured
LMArena Text: PolishNot measured1423Only MiniMax M3 measured
LMArena Text: multi-turnNot measured1443Only MiniMax M3 measured
LMArena Text: longer queriesNot measured1446Only MiniMax M3 measured
LMArena Text: writing and languageNot measured1419Only MiniMax M3 measured
LMArena Text: entertainment and mediaNot measured1403Only MiniMax M3 measured
LMArena Vision: EnglishNot measured1263Only MiniMax M3 measured
LMArena Vision: ChineseNot measured1311Only MiniMax M3 measured
LMArena Vision: reading textNot measured1259Only MiniMax M3 measured
LMArena Vision: humorNot measured1235Only MiniMax M3 measured
LMArena Vision: recognizing thingsNot measured1197Only MiniMax M3 measured
LMArena Vision: creative writingNot measured1234Only MiniMax M3 measured
LMArena DocumentNot measured1435Only MiniMax M3 measured
EQ-Bench 4Not measured1150Only MiniMax M3 measured
Neither model has a result on the other 12 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Mercury 2.5 and MiniMax M3
BenchmarkMercury 2.5MiniMax M3Leader
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

Mercury 2.5$0.0001Fits in one request
MiniMax M3$0.0009Fits in one request

Mercury 2.5 costs less

Repository review

50K input + 3K output tokens

Mercury 2.5$0.0024Fits in one request
MiniMax M3$0.019Fits in one request

Mercury 2.5 costs less

Agent loop

200K input + 10K output tokens

Mercury 2.5$0.0095Fits in one request
MiniMax M3$0.072Fits in one request

Mercury 2.5 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 Mercury 2.5 and MiniMax M3
SpecificationInception Mercury 2.5MiniMax M3
MakerInceptionMiniMax
WeightsNo public weights listedOpen weights
ReleasedSeptember 8, 2026May 31, 2026
Context window260K1.05M
Input $/Mtok$0.04$0.30
Output $/Mtok$0.15$1.20
Coding index1.639.2
Independent measurements behind it26
Cost per solved taskNot computable$0.56
SourceOpenRouter listingOpenRouter listing

Questions

Is Mercury 2.5 better than MiniMax M3 for coding?

Pick MiniMax M3 for coding: it scores 39.2 on the Vibe Coding Index against 1.6 for Mercury 2.5. Pick Mercury 2.5 for output tokens 8.0x cheaper ($0.15 vs $1.20 per million).

Which is cheaper, Mercury 2.5 or MiniMax M3?

Mercury 2.5 costs $0.04 per million input tokens and $0.15 per million output tokens; MiniMax M3 costs $0.30 and $1.20. Cost per solved task is known for MiniMax M3 only.

Which has the bigger context window, Mercury 2.5 or MiniMax M3?

MiniMax M3, with 1.05M tokens against 260K.

How many benchmarks is the Mercury 2.5 vs MiniMax M3 comparison based on?

20 benchmarks have a result for both models as of October 22, 2026. Mercury 2.5's coding index rests on 2 independent benchmarks and MiniMax M3's on 6. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/inception-mercury-2-5-vs-minimax-minimax-m3" title="Mercury 2.5 vs MiniMax M3, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/inception-mercury-2-5-vs-minimax-minimax-m3">LLMBenchmark.ai, Mercury 2.5 vs MiniMax M3</a></p>