Model comparison

Mercury 2 vs MiniMax-M2.7

Mercury 2 is the stronger model overall, scoring 39.1 to 37.7 on the Noometry Index.

Last verified October 10, 2026. 17 shared benchmarks.

Mercury 2 Inception

39.1

Rank #175 Confirmed

MiniMax-M2.7

MiniMax

37.7

Rank #196 Confirmed

Summary

They share 17 benchmarks with published results for both. Mercury 2 scores higher in 1 category and MiniMax-M2.7 in 6 categories; 7 gaps are clear of the uncertainty.
The widest gap is in coding, where MiniMax-M2.7 leads 41.8 to 33.5.
The biggest single-benchmark swing is SciCode: 38.7% for Mercury 2 and 47% for MiniMax-M2.7.
Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.7.
MiniMax-M2.7 accepts more context: 205K tokens versus 128K.
MiniMax-M2.7 has downloadable open weights; the other is API-only.

Side by side

Mercury 2 and MiniMax-M2.7 specifications
	Mercury 2	MiniMax-M2.7
Provider	Inception	MiniMax
Noometry Index	39.1	37.7
Released	2026-02-20	2026-03-18
Weights	Proprietary	Open
Context window	128K	205K
Max output	50K	131K
Input $ / M tokens	$0.25	$0.30
Output $ / M tokens	$0.75	$1.20
Results tracked	17	30

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding MiniMax-M2.7 leads

Mercury 2: 33.5 (#255), MiniMax-M2.7: 41.8 (#120)

Coding benchmarks
Benchmark	Mercury 2	MiniMax-M2.7
LMArena WebDev	1171	1398
SciCode	38.7%	47%
WeirdML	43.2%	37%
LMArena Coding	1391	1454
ALE-Bench	785.58	599.25

Agentic & Tool Use Not comparable

Mercury 2: —, MiniMax-M2.7: 25.1 (#111)

Agentic & Tool Use benchmarks
Benchmark	Mercury 2	MiniMax-M2.7
Terminal-Bench	—	45.1%
ExploitBench	—	13.3%
GBAEval	—	0%

Reasoning Mercury 2 leads

Mercury 2: 23.8 (#170), MiniMax-M2.7: 19.7 (#253)

Reasoning benchmarks
Benchmark	Mercury 2	MiniMax-M2.7
CritPt	0.8%	0.6%
LMArena Hard Prompts	1362	1422
NYT Connections (extended)	—	24.7%
Thematic Generalization	—	39.3%
Epoch Capabilities Index	—	145.85

Math Not comparable

Mercury 2: —, MiniMax-M2.7: 25.9 (#263)

Math benchmarks
Benchmark	Mercury 2	MiniMax-M2.7
ProofBench	—	3%
LMArena Math	—	1420

Knowledge MiniMax-M2.7 leads

Mercury 2: 36.2 (#172), MiniMax-M2.7: 37.7 (#152)

Knowledge benchmarks
Benchmark	Mercury 2	MiniMax-M2.7
Vectara Hallucination Rate	12.3%	12.9%
LMArena Expert	1358	1444

Multilingual MiniMax-M2.7 leads

Mercury 2: 46.6 (#157), MiniMax-M2.7: 50.3 (#123)

Multilingual benchmarks
Benchmark	Mercury 2	MiniMax-M2.7
LMArena Non-English	1331	1382
LMArena Chinese	1417	1441
LMArena Russian	1304	1383
LMArena French	—	1421
LMArena German	—	1398
LMArena Japanese	—	1262
LMArena Korean	—	1313
LMArena Spanish	—	1403

Instruction Following MiniMax-M2.7 leads

Mercury 2: 70.2 (#165), MiniMax-M2.7: 74.1 (#103)

Instruction Following benchmarks
Benchmark	Mercury 2	MiniMax-M2.7
LMArena Instruction Following	1329	1405

Long Context MiniMax-M2.7 leads

Mercury 2: 40.5 (#154), MiniMax-M2.7: 43.3 (#99)

Long Context benchmarks
Benchmark	Mercury 2	MiniMax-M2.7
LMArena Longer Query	1330	1419

Writing & Preference MiniMax-M2.7 leads

Mercury 2: 53.8 (#155), MiniMax-M2.7: 58.9 (#112)

Writing & Preference benchmarks
Benchmark	Mercury 2	MiniMax-M2.7
LMArena Text	1355	1405
LMArena Creative Writing	1289	1354
LMArena Multi-Turn	1358	1412

Frequently asked questions

Is Mercury 2 better than MiniMax-M2.7?

Mercury 2 is the stronger model overall, scoring 39.1 to 37.7 on the Noometry Index.

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

Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; MiniMax-M2.7 lists at $0.30 and $1.20.

Is Mercury 2 or MiniMax-M2.7 better for coding?

MiniMax-M2.7 scores higher on coding benchmarks: 41.8 versus 33.5 in the Noometry coding category.

Which has the bigger context window?

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

How many benchmarks do Mercury 2 and MiniMax-M2.7 share?

17 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and MiniMax-M2.7 has 30.