Enter opens the highlighted result. Esc closes.

Mercury 2 vs MiniMax M2.7

MiniMax M2.7 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; 42 benchmarks have a result for both.

Replace Mercury 2 Replace MiniMax M2.7
Mercury 2Inception
Coding
No data
Overall
No data
Output $/M
$0.75
2
MiniMax M2.7MiniMax
Coding
36.2
Overall
44.5
Output $/M
$1.20
40
vs boards won of 42 shared

Mercury 2 or MiniMax M2.7: which to pick

Only MiniMax M2.7 has a coding score, 36.2 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 WeirdML or ALE-Bench, where it leads.

Model AMercury 2InceptionNot benchmarked1 independent benchmarkNo cost per solved taskModel BMiniMax M2.7MiniMax36.2/1003 independent benchmarks$0.64 per solved task
Shared results
42
Mercury 2 only
0
MiniMax M2.7 only
32
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 M2.7 36.2 from 3 benchmarks.
Widest category
Web design, 24.7 points apart on average over 8 shared benchmarks.
Widest single gap
LMArena WebDev: React: Mercury 2 1160 against MiniMax M2.7 1388, 38.0 points apart on a 0 to 100 scale.
Output price
Mercury 2 $0.75 against MiniMax M2.7 $1.20 per million output tokens, 1.6x apart.
Context window
Mercury 2 takes 128K tokens, MiniMax M2.7 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 M2.7Ties
Coding28
Intelligence01
Agentic work02
Reasoning05
Knowledge03
Web design08
General013
All shared boards240
CodingLike-for-likeSix of these boards feed the Vibe Coding Index28
Coding benchmarks for Mercury 2 and MiniMax M2.7
BenchmarkMercury 2MiniMax M2.7Leader
LMArena WebDev11711399MiniMax M2.7
AA Coding Index31.152.6MiniMax M2.7
LiveCodeBench (Vals AI)Not measured79.9%Only MiniMax M2.7 measured
SWE-bench Verified (Vals AI)Not measured73.8%Only MiniMax M2.7 measured
Vibe Code Bench (Vals AI)Not measured11.9%Only MiniMax M2.7 measured
Code migration (Vals AI)Not measured8.7%Only MiniMax M2.7 measured
ProgramBench (Vals AI)Not measured0.0%Only MiniMax M2.7 measured
Terminal-Bench 2.1 (Vals AI)Not measured48.7%Only MiniMax M2.7 measured
SciCode37.7%50.1%MiniMax M2.7
Terminal-Bench Hard (Artificial Analysis run)26.5%39.4%MiniMax M2.7
Terminal-BenchNot measured45.1%Only MiniMax M2.7 measured
WeirdML43.2%37.0%Mercury 2
ALE-Bench785.6599.3Mercury 2
LMArena Text: coding13901454MiniMax M2.7
LMArena Text: software and IT13851446MiniMax M2.7
LMArena WebDev: React11601388MiniMax M2.7
LMArena WebDev: HTML11991401MiniMax M2.7
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 Mercury 2 and MiniMax M2.7
BenchmarkMercury 2MiniMax M2.7Leader
AA Intelligence Index10.822.8MiniMax M2.7
Epoch Capabilities IndexNot measured145.8Only MiniMax M2.7 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
Agentic work benchmarks for Mercury 2 and MiniMax M2.7
BenchmarkMercury 2MiniMax M2.7Leader
AA Agentic Index1.615.3MiniMax M2.7
Finance Agent (Vals AI)Not measured27.9%Only MiniMax M2.7 measured
Tax Agent Bench (Vals AI)Not measured6.9%Only MiniMax M2.7 measured
Legal Research Bench (Vals AI)Not measured10.6%Only MiniMax M2.7 measured
Excel Modeling Benchmark (Vals AI)Not measured28.4%Only MiniMax M2.7 measured
τ²-Bench Telecom70.8%84.8%MiniMax M2.7
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 Mercury 2 and MiniMax M2.7
BenchmarkMercury 2MiniMax M2.7Leader
GPQA DiamondNot measured86.6%Only MiniMax M2.7 measured
GPQA Diamond (Artificial Analysis run)77.0%87.4%MiniMax M2.7
Humanity's Last Exam (Artificial Analysis run)17.1%29.6%MiniMax M2.7
LMArena Text: hard prompts13621422MiniMax M2.7
LMArena Text: expert13581443MiniMax M2.7
LMArena Text: hard prompts in English13741441MiniMax M2.7
Neither model has a result on the other 17 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
Math benchmarks for Mercury 2 and MiniMax M2.7
BenchmarkMercury 2MiniMax M2.7Leader
AIMENot measured91.0%Only MiniMax M2.7 measured
ProofBenchNot measured3.0%Only MiniMax M2.7 measured
LMArena Text: mathNot measured1421Only MiniMax M2.7 measured
LMArena Text: mathematical workNot measured1437Only MiniMax M2.7 measured
Neither model has a result on the other 10 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index03
Knowledge benchmarks for Mercury 2 and MiniMax M2.7
BenchmarkMercury 2MiniMax M2.7Leader
MMLU ProNot measured80.4%Only MiniMax M2.7 measured
LegalBench (Vals AI)Not measured84.0%Only MiniMax M2.7 measured
CaseLaw (Vals AI)Not measured60.9%Only MiniMax M2.7 measured
CorpFin (Vals AI)Not measured61.2%Only MiniMax M2.7 measured
TaxEval (Vals AI)Not measured66.6%Only MiniMax M2.7 measured
MedCode (Vals AI)Not measured34.4%Only MiniMax M2.7 measured
LMArena Text: science13431416MiniMax M2.7
LMArena Text: medicine and healthcare13631409MiniMax M2.7
LMArena Text: legal and governmentNot measured1403Only MiniMax M2.7 measured
LMArena Text: business and finance13491407MiniMax M2.7
Neither model has a result on the other 10 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index08
Web design benchmarks for Mercury 2 and MiniMax M2.7
BenchmarkMercury 2MiniMax M2.7Leader
Design Arena: websites10351242MiniMax M2.7
Design Arena: UI components9961207MiniMax M2.7
Design Arena: game dev9831209MiniMax M2.7
Design Arena: data viz10101233MiniMax M2.7
Design Arena: 3D9821194MiniMax M2.7
Design Arena: all code categories10211233MiniMax M2.7
Design Arena: SVG9971137MiniMax M2.7
Design Arena: ASCII art9881136MiniMax M2.7
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index013
General benchmarks for Mercury 2 and MiniMax M2.7
BenchmarkMercury 2MiniMax M2.7Leader
MedScribe (Vals AI)Not measured79.9%Only MiniMax M2.7 measured
IFBench69.8%75.7%MiniMax M2.7
Long context reasoning (AA-LCR)43.7%78.3%MiniMax M2.7
ExploitBenchNot measured13.3%Only MiniMax M2.7 measured
LMArena Text13541405MiniMax M2.7
LMArena Text: instruction following13281405MiniMax M2.7
LMArena Text: creative writing12861354MiniMax M2.7
LMArena Text: English13781426MiniMax M2.7
LMArena Text: non-English13301382MiniMax M2.7
LMArena Text: Chinese14141442MiniMax M2.7
LMArena Text: GermanNot measured1398Only MiniMax M2.7 measured
LMArena Text: JapaneseNot measured1260Only MiniMax M2.7 measured
LMArena Text: KoreanNot measured1314Only MiniMax M2.7 measured
LMArena Text: FrenchNot measured1424Only MiniMax M2.7 measured
LMArena Text: SpanishNot measured1402Only MiniMax M2.7 measured
LMArena Text: Russian13041383MiniMax M2.7
LMArena Text: PolishNot measured1387Only MiniMax M2.7 measured
LMArena Text: multi-turn13571412MiniMax M2.7
LMArena Text: longer queries13291418MiniMax M2.7
LMArena Text: writing and language13001376MiniMax M2.7
LMArena Text: entertainment and media13141360MiniMax M2.7
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 Mercury 2 and MiniMax M2.7
BenchmarkMercury 2MiniMax M2.7Leader
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 M2.7$0.0009Fits in one request

Mercury 2 costs less

Repository review

50K input + 3K output tokens

Mercury 2$0.015Fits in one request
MiniMax M2.7$0.019Fits in one request

Mercury 2 costs less

Agent loop

200K input + 10K output tokens

Mercury 2$0.058Exceeds the context window
MiniMax M2.7$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 M2.7
SpecificationInception Mercury 2MiniMax M2.7
MakerInceptionMiniMax
WeightsNo public weights listedOpen weights
ReleasedMarch 4, 2026March 18, 2026
Context window128K205K
Input $/Mtok$0.25$0.30
Output $/Mtok$0.75$1.20
Coding indexNot benchmarked36.2
Independent measurements behind it13
Cost per solved taskNot computable$0.64
SourceOpenRouter listingOpenRouter listing

Questions

Is Mercury 2 better than MiniMax M2.7 for coding?

Only MiniMax M2.7 has a coding score, 36.2 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 WeirdML or ALE-Bench, where it leads.

Which is cheaper, Mercury 2 or MiniMax M2.7?

Mercury 2 costs $0.25 per million input tokens and $0.75 per million output tokens; MiniMax M2.7 costs $0.30 and $1.20. Cost per solved task is known for MiniMax M2.7 only.

Which has the bigger context window, Mercury 2 or MiniMax M2.7?

MiniMax M2.7, with 205K tokens against 128K.

How many benchmarks is the Mercury 2 vs MiniMax M2.7 comparison based on?

42 benchmarks have a result for both models as of October 22, 2026. Mercury 2's coding index rests on 1 independent benchmark and MiniMax M2.7's on 3. Where only one model has a result, the page says so instead of naming a winner.

Compare next