Noometry

Model comparison

Grok 4.6 vs MiniMax-M2.7

Grok 4.6 is the stronger model overall, scoring 56.8 to 37.4 on the Noometry Index. MiniMax-M2.7 costs 5.7× less per token, which makes it the better buy when Grok 4.6's lead doesn't matter for your workload.

Last verified . 25 shared benchmarks.

Grok 4.6 xAI

56.8

Rank #19 Confirmed

MiniMax-M2.7 MiniMax

37.4

Rank #188 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Grok 4.6 scores higher in 9 categories and MiniMax-M2.7 in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4.6 leads 61.3 to 19.0.
  • The biggest single-benchmark swing is NYT Connections (extended): 80% for Grok 4.6 and 24.7% for MiniMax-M2.7.
  • MiniMax-M2.7 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2 / $6 for Grok 4.6.
  • Grok 4.6 accepts more context: 500K tokens versus 205K.
  • MiniMax-M2.7 has downloadable open weights; the other is API-only.

Side by side

Grok 4.6MiniMax-M2.7
ProviderxAIMiniMax
Noometry Index56.837.4
Released2026-08-122026-03-18
WeightsProprietaryOpen
Context window500K205K
Max output500K131K
Input $ / M tokens$2$0.30
Output $ / M tokens$6$1.20
Results tracked4930

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

Category by category

Coding Grok 4.6 leads

Grok 4.6: 58.0 (#14), MiniMax-M2.7: 41.4 (#115)

BenchmarkGrok 4.6MiniMax-M2.7
LMArena WebDev16201397
SciCode56.5%47%
WeirdML67.3%37%
LMArena Coding14641454
ALE-Bench1,508599.25
DeepSWE67.5%—
FrontierCode48%—
CursorBench41.4%—
FrontierSWE25.3%—

Agentic & Tool Use Grok 4.6 leads

Grok 4.6: 39.4 (#25), MiniMax-M2.7: 24.9 (#103)

BenchmarkGrok 4.6MiniMax-M2.7
Terminal-Bench—45.1%
APEX-Agents65.3%—
ExploitBench—13.3%
GBAEval—0%
GDP.pdf17.2%—
Vending-Bench 29,047—

Reasoning Grok 4.6 leads

Grok 4.6: 61.3 (#18), MiniMax-M2.7: 19.0 (#248)

BenchmarkGrok 4.6MiniMax-M2.7
NYT Connections (extended)80%24.7%
CritPt19.7%0.6%
LMArena Hard Prompts14451422
Epoch Capabilities Index156.48145.84
ARC-AGI-267.1%—
SimpleBench75.9%—
ARC-AGI-187.5%—
Chess Puzzles40%—
Thematic Generalization—39.3%
EBR-Bench30.5%—
Mystery Game Puzzles34%—
DTBench97.3%—
LMCA48.5%—

Math Grok 4.6 leads

Grok 4.6: 66.8 (#19), MiniMax-M2.7: 24.9 (#254)

BenchmarkGrok 4.6MiniMax-M2.7
ProofBench51%3%
LMArena Math14161420
FrontierMath (Tiers 1-3)66%—
FrontierMath Tier 431.7%—
OTIS Mock AIME 2024-202599.2%—

Knowledge Grok 4.6 leads

Grok 4.6: 63.3 (#18), MiniMax-M2.7: 37.1 (#151)

BenchmarkGrok 4.6MiniMax-M2.7
LMArena Expert14631443
GPQA Diamond94%—
SimpleQA Verified49.3%—
Vectara Hallucination Rate—12.9%

Multimodal Not comparable

Grok 4.6: 43.9 (#18), MiniMax-M2.7: —

BenchmarkGrok 4.6MiniMax-M2.7
LMArena Vision1265—
Blueprint-Bench 233.2%—
Furniture Assembly40%—
LMArena Document1452—

Multilingual Grok 4.6 leads

Grok 4.6: 53.3 (#67), MiniMax-M2.7: 50.5 (#120)

BenchmarkGrok 4.6MiniMax-M2.7
LMArena Non-English14221382
LMArena Chinese14791439
LMArena French14581422
LMArena German14251398
LMArena Japanese13831261
LMArena Korean13951313
LMArena Russian14271383
LMArena Spanish14081403

Instruction Following Grok 4.6 leads

Grok 4.6: 75.6 (#59), MiniMax-M2.7: 74.2 (#101)

BenchmarkGrok 4.6MiniMax-M2.7
LMArena Instruction Following14311404

Long Context Grok 4.6 leads

Grok 4.6: 44.4 (#62), MiniMax-M2.7: 43.3 (#94)

BenchmarkGrok 4.6MiniMax-M2.7
LMArena Longer Query14531419

Writing & Preference Grok 4.6 leads

Grok 4.6: 62.5 (#77), MiniMax-M2.7: 59.1 (#107)

BenchmarkGrok 4.6MiniMax-M2.7
LMArena Text14271404
LMArena Creative Writing14301354
LMArena Multi-Turn14221413

Frequently asked questions

Is Grok 4.6 better than MiniMax-M2.7?

Grok 4.6 is the stronger model overall, scoring 56.8 to 37.4 on the Noometry Index. MiniMax-M2.7 costs 5.7× less per token, which makes it the better buy when Grok 4.6's lead doesn't matter for your workload.

Which is cheaper, Grok 4.6 or MiniMax-M2.7?

MiniMax-M2.7 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Grok 4.6 lists at $2 and $6.

Is Grok 4.6 or MiniMax-M2.7 better for coding?

Grok 4.6 scores higher on coding benchmarks: 58.0 versus 41.4 in the Noometry coding category.

Which has the bigger context window?

Grok 4.6 does, with 500K tokens against 205K.

How many benchmarks do Grok 4.6 and MiniMax-M2.7 share?

25 benchmarks have published results for both models. Grok 4.6 has 49 scored results on Noometry and MiniMax-M2.7 has 30.

Related comparisons

Go deeper