Enter opens the highlighted result. Esc closes.

Mercury 2 vs MiniMax M2.5

MiniMax M2.5 leads Mercury 2 on the Artificial Analysis Intelligence Index, 22.8 to 10.8, and Mercury 2 costs 1.6x less per output token ($0.75 vs $1.20 per million). Updated October 22, 2026; 37 benchmarks have a result for both.

Replace Mercury 2 Replace MiniMax M2.5
Mercury 2Inception
Coding
No data
Overall
No data
Output $/M
$0.75
5
MiniMax M2.5MiniMax
Coding
37.2
Overall
37.3
Output $/M
$1.20
32
vs boards won of 37 shared

Mercury 2 or MiniMax M2.5: which to pick

Only MiniMax M2.5 has a coding score, 37.2 on the Vibe Coding Index; Mercury 2 has none, so the two cannot be ranked on coding.

Pick Mercury 2 for output tokens 1.6x cheaper ($0.75 vs $1.20 per million) and work measured by ALE-Bench or LMArena Text: coding, where it leads.

Model AMercury 2InceptionNot benchmarked1 independent benchmarkNo cost per solved taskModel BMiniMax M2.5MiniMax37.2/1003 independent benchmarks$0.62 per solved task
Shared results
37
Mercury 2 only
5
MiniMax M2.5 only
31
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 not benchmarked, MiniMax M2.5 37.2 from 3 benchmarks.
Widest category
Agentic work, 24.6 points apart on average over 1 shared benchmark.
Widest single gap
LMArena WebDev: HTML: Mercury 2 1199 against MiniMax M2.5 1414, 35.7 points apart on a 0 to 100 scale.
Output price
Mercury 2 $0.75 against MiniMax M2.5 $1.20 per million output tokens, 1.6x apart.
Context window
Mercury 2 takes 128K tokens, MiniMax M2.5 205K.

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 2BarsMiniMax M2.5Ties
Coding34
Intelligence01
Agentic work01
Reasoning05
Knowledge12
Web design07
General112
All shared boards532
CodingLike-for-likeSix of these boards feed the Vibe Coding Index34
Coding benchmarks for Mercury 2 and MiniMax M2.5
BenchmarkMercury 2MiniMax M2.5Leader
SWE-bench VerifiedNot measured75.8%Only MiniMax M2.5 measured
SWE-bench MultilingualNot measured68.3%Only MiniMax M2.5 measured
LMArena WebDev11711386MiniMax M2.5
AA Coding Index31.1Not measuredOnly Mercury 2 measured
LiveCodeBench (Vals AI)Not measured79.2%Only MiniMax M2.5 measured
SWE-bench Verified (Vals AI)Not measured74.2%Only MiniMax M2.5 measured
Vibe Code Bench (Vals AI)Not measured14.8%Only MiniMax M2.5 measured
SciCode37.7%Not measuredOnly Mercury 2 measured
Terminal-Bench Hard (Artificial Analysis run)26.5%34.8%MiniMax M2.5
Terminal-BenchNot measured42.7%Only MiniMax M2.5 measured
WeirdML43.2%Not measuredOnly Mercury 2 measured
ALE-Bench785.6618.2Mercury 2
LMArena Text: coding13901380Mercury 2
LMArena Text: software and IT13851383Mercury 2
LMArena WebDev: React11601374MiniMax M2.5
LMArena WebDev: HTML11991414MiniMax M2.5
Neither model has a result on the other 23 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Mercury 2 and MiniMax M2.5
BenchmarkMercury 2MiniMax M2.5Leader
AA Intelligence Index10.822.8MiniMax M2.5
Epoch Capabilities IndexNot measured146.6Only MiniMax M2.5 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Mercury 2 and MiniMax M2.5
BenchmarkMercury 2MiniMax M2.5Leader
AA Agentic Index1.6Not measuredOnly Mercury 2 measured
τ²-Bench Telecom70.8%95.3%MiniMax M2.5
Vending-Bench 2Not measured-$23Only MiniMax M2.5 measured
Neither model has a result on the other 38 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
Reasoning benchmarks for Mercury 2 and MiniMax M2.5
BenchmarkMercury 2MiniMax M2.5Leader
GPQA DiamondNot measured82.1%Only MiniMax M2.5 measured
GPQA Diamond (Artificial Analysis run)77.0%84.8%MiniMax M2.5
Humanity's Last Exam (Artificial Analysis run)17.1%20.5%MiniMax M2.5
ARC-AGINot measured63.7%Only MiniMax M2.5 measured
ARC-AGI-2Not measured4.9%Only MiniMax M2.5 measured
LMArena Text: hard prompts13621372MiniMax M2.5
LMArena Text: expert13581378MiniMax M2.5
LMArena Text: hard prompts in English13741384MiniMax M2.5
Kagi LLM BenchmarkNot measured55.2%Only MiniMax M2.5 measured
Neither model has a result on the other 13 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
Math benchmarks for Mercury 2 and MiniMax M2.5
BenchmarkMercury 2MiniMax M2.5Leader
AIMENot measured88.8%Only MiniMax M2.5 measured
ProofBenchNot measured4.0%Only MiniMax M2.5 measured
LMArena Text: mathNot measured1378Only MiniMax M2.5 measured
LMArena Text: mathematical workNot measured1378Only MiniMax M2.5 measured
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index12
Knowledge benchmarks for Mercury 2 and MiniMax M2.5
BenchmarkMercury 2MiniMax M2.5Leader
MMLU ProNot measured80.1%Only MiniMax M2.5 measured
LegalBench (Vals AI)Not measured80.0%Only MiniMax M2.5 measured
CaseLaw (Vals AI)Not measured53.5%Only MiniMax M2.5 measured
CorpFin (Vals AI)Not measured59.6%Only MiniMax M2.5 measured
TaxEval (Vals AI)Not measured68.2%Only MiniMax M2.5 measured
MedQA (Vals AI)Not measured92.5%Only MiniMax M2.5 measured
LMArena Text: science13431369MiniMax M2.5
LMArena Text: medicine and healthcare13631357Mercury 2
LMArena Text: legal and governmentNot measured1366Only MiniMax M2.5 measured
LMArena Text: business and finance13491356MiniMax M2.5
Neither model has a result on the other 8 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index07
Web design benchmarks for Mercury 2 and MiniMax M2.5
BenchmarkMercury 2MiniMax M2.5Leader
Design Arena: websites10361222MiniMax M2.5
Design Arena: UI components9961173MiniMax M2.5
Design Arena: game dev9841176MiniMax M2.5
Design Arena: data viz10091172MiniMax M2.5
Design Arena: 3D9821170MiniMax M2.5
Design Arena: all code categories10211207MiniMax M2.5
Design Arena: SVG9981150MiniMax M2.5
Design Arena: ASCII art988Not measuredOnly Mercury 2 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index112
General benchmarks for Mercury 2 and MiniMax M2.5
BenchmarkMercury 2MiniMax M2.5Leader
IFBench69.8%71.6%MiniMax M2.5
Long context reasoning (AA-LCR)43.7%73.3%MiniMax M2.5
CL-benchNot measured11.4%Only MiniMax M2.5 measured
CL-bench LifeNot measured6.3%Only MiniMax M2.5 measured
LMArena Text13541359MiniMax M2.5
LMArena Text: instruction following13281353MiniMax M2.5
LMArena Text: creative writing12861331MiniMax M2.5
LMArena Text: English13781380MiniMax M2.5
LMArena Text: non-English13301338MiniMax M2.5
LMArena Text: Chinese14141393Mercury 2
LMArena Text: GermanNot measured1361Only MiniMax M2.5 measured
LMArena Text: JapaneseNot measured1171Only MiniMax M2.5 measured
LMArena Text: KoreanNot measured1233Only MiniMax M2.5 measured
LMArena Text: FrenchNot measured1363Only MiniMax M2.5 measured
LMArena Text: SpanishNot measured1353Only MiniMax M2.5 measured
LMArena Text: Russian13041359MiniMax M2.5
LMArena Text: PolishNot measured1334Only MiniMax M2.5 measured
LMArena Text: multi-turn13571364MiniMax M2.5
LMArena Text: longer queries13291366MiniMax M2.5
LMArena Text: writing and language13001345MiniMax M2.5
LMArena Text: entertainment and media13141329MiniMax M2.5
Neither model has a result on the other 25 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Mercury 2 and MiniMax M2.5
BenchmarkMercury 2MiniMax M2.5Leader
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$0.0006Fits in one request
MiniMax M2.5$0.0009Fits in one request

Mercury 2 costs less

Repository review

50K input + 3K output tokens

Mercury 2$0.015Fits in one request
MiniMax M2.5$0.019Fits in one request

Mercury 2 costs less

Agent loop

200K input + 10K output tokens

Mercury 2$0.058Exceeds the context window
MiniMax M2.5$0.072Exceeds the context window

Mercury 2 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 and MiniMax M2.5
SpecificationInception Mercury 2MiniMax M2.5
MakerInceptionMiniMax
WeightsNo public weights listedOpen weights
ReleasedMarch 4, 2026February 12, 2026
Context window128K205K
Input $/Mtok$0.25$0.30
Output $/Mtok$0.75$1.20
Coding indexNot benchmarked37.2
Independent measurements behind it13
Cost per solved taskNot computable$0.62
SourceOpenRouter listingOpenRouter listing

Questions

Is Mercury 2 better than MiniMax M2.5 for coding?

Only MiniMax M2.5 has a coding score, 37.2 on the Vibe Coding Index; Mercury 2 has none, so the two cannot be ranked on coding. Pick Mercury 2 for output tokens 1.6x cheaper ($0.75 vs $1.20 per million) and work measured by ALE-Bench or LMArena Text: coding, where it leads.

Which is cheaper, Mercury 2 or MiniMax M2.5?

Mercury 2 costs $0.25 per million input tokens and $0.75 per million output tokens; MiniMax M2.5 costs $0.30 and $1.20. Cost per solved task is known for MiniMax M2.5 only.

Which has the bigger context window, Mercury 2 or MiniMax M2.5?

MiniMax M2.5, with 205K tokens against 128K.

How many benchmarks is the Mercury 2 vs MiniMax M2.5 comparison based on?

37 benchmarks have a result for both models as of October 22, 2026. Mercury 2's coding index rests on 1 independent benchmark and MiniMax M2.5's on 3. Where only one model has a result, the page says so instead of naming a winner.

Compare next