Noometry

Model comparison

Grok 4.5 vs MiniMax-M3

Grok 4.5 is the stronger model overall, scoring 55.0 to 43.8 on the Noometry Index. MiniMax-M3 costs 5.7× less per token, which makes it the better buy when Grok 4.5's lead doesn't matter for your workload.

Last verified . 37 shared benchmarks.

Grok 4.5 xAI

55.0

Rank #25 Confirmed

MiniMax-M3 MiniMax

43.8

Rank #85 Confirmed

Summary

  • They share 37 benchmarks with published results for both. Grok 4.5 scores higher in 9 categories and MiniMax-M3 in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4.5 leads 56.1 to 30.1.
  • The biggest single-benchmark swing is GBAEval: 65.4% for Grok 4.5 and 0.9% for MiniMax-M3.
  • MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2 / $6 for Grok 4.5.
  • MiniMax-M3 accepts more context: 1M tokens versus 500K.
  • MiniMax-M3 has downloadable open weights; the other is API-only.

Side by side

Grok 4.5MiniMax-M3
ProviderxAIMiniMax
Noometry Index55.043.8
Released2026-07-082026-06-01
WeightsProprietaryOpen
Context window500K1M
Max output500K512K
Input $ / M tokens$2$0.30
Output $ / M tokens$6$1.20
Results tracked5241

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

Category by category

Coding Grok 4.5 leads

Grok 4.5: 52.2 (#35), MiniMax-M3: 41.8 (#118)

BenchmarkGrok 4.5MiniMax-M3
FrontierCode42.4%14.7%
LMArena WebDev15531482
SciCode54.1%47.1%
LMArena Coding14741469
ALE-Bench1,309640.02
DeepSWE53.8%—
WeirdML46.4%—

Agentic & Tool Use Grok 4.5 leads

Grok 4.5: 44.4 (#17), MiniMax-M3: 22.6 (#130)

BenchmarkGrok 4.5MiniMax-M3
APEX-Agents56.2%37.7%
GBAEval65.4%0.9%
Vending-Bench 23,8872,158
OSWorld 2.0—4.6%
τ²-bench Banking47.9%—
PostTrainBench23.4%—
GDP.pdf14%—
LMArena Search1213—

Reasoning Grok 4.5 leads

Grok 4.5: 56.1 (#25), MiniMax-M3: 30.1 (#87)

BenchmarkGrok 4.5MiniMax-M3
SimpleBench70%45.8%
NYT Connections (extended)79.9%65.1%
CritPt15.4%3.7%
Chess Puzzles36%14%
LMArena Hard Prompts14621447
DTBench96.5%78.9%
LMCA45.2%33.7%
Surface Evolver Bench74.4%55%
Epoch Capabilities Index153.92146.95
ARC-AGI-252.6%—
Kagi LLM Benchmark83.5%—
ARC-AGI-187.2%—
Mystery Game Puzzles—8%
ForecastBench—61.4

Math Grok 4.5 leads

Grok 4.5: 60.9 (#35), MiniMax-M3: 40.0 (#95)

BenchmarkGrok 4.5MiniMax-M3
OTIS Mock AIME 2024-202597.8%71.1%
ProofBench31%18%
LMArena Math14591429
FrontierMath (Tiers 1-3)57.2%—
FrontierMath Tier 424.4%—

Knowledge Grok 4.5 leads

Grok 4.5: 62.3 (#24), MiniMax-M3: 58.4 (#35)

BenchmarkGrok 4.5MiniMax-M3
GPQA Diamond93.4%90.9%
LMArena Expert14661461
SimpleQA Verified48.3%—

Multimodal MiniMax-M3 leads

Grok 4.5: 37.6 (#72), MiniMax-M3: 40.2 (#51)

BenchmarkGrok 4.5MiniMax-M3
LMArena Vision12881253
LMArena Document14521435
Blueprint-Bench 227.3%—
Furniture Assembly22.5%—

Multilingual Grok 4.5 leads

Grok 4.5: 54.4 (#42), MiniMax-M3: 53.0 (#75)

BenchmarkGrok 4.5MiniMax-M3
LMArena Non-English14401420
LMArena Chinese14961463
LMArena French14561447
LMArena German14461426
LMArena Japanese14281381
LMArena Korean14041372
LMArena Russian14481428
LMArena Spanish14501432

Instruction Following Too close to call

Grok 4.5: 76.0 (#48), MiniMax-M3: 75.5 (#62)

BenchmarkGrok 4.5MiniMax-M3
LMArena Instruction Following14461433

Long Context Too close to call

Grok 4.5: 44.8 (#56), MiniMax-M3: 44.2 (#72)

BenchmarkGrok 4.5MiniMax-M3
LMArena Longer Query14631445

Writing & Preference Grok 4.5 leads

Grok 4.5: 65.8 (#42), MiniMax-M3: 62.1 (#83)

BenchmarkGrok 4.5MiniMax-M3
LMArena Text14481433
LMArena Creative Writing14421404
LMArena Multi-Turn14561442
EQ-Bench Creative Writing1579—
EQ-Bench 4—1150

Frequently asked questions

Is Grok 4.5 better than MiniMax-M3?

Grok 4.5 is the stronger model overall, scoring 55.0 to 43.8 on the Noometry Index. MiniMax-M3 costs 5.7× less per token, which makes it the better buy when Grok 4.5's lead doesn't matter for your workload.

Which is cheaper, Grok 4.5 or MiniMax-M3?

MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Grok 4.5 lists at $2 and $6.

Is Grok 4.5 or MiniMax-M3 better for coding?

Grok 4.5 scores higher on coding benchmarks: 52.2 versus 41.8 in the Noometry coding category.

Which has the bigger context window?

MiniMax-M3 does, with 1M tokens against 500K.

How many benchmarks do Grok 4.5 and MiniMax-M3 share?

37 benchmarks have published results for both models. Grok 4.5 has 52 scored results on Noometry and MiniMax-M3 has 41.

Related comparisons

Go deeper