Model comparison

Grok 2 Mini 2024 08 13 vs MiniMax-M2.5

Grok 2 Mini 2024 08 13 and MiniMax-M2.5 score almost the same on the Noometry Index (37.7 vs 38.3), so choose on price, context window or the category you care about most.

Last verified . 17 shared benchmarks.

Grok 2 Mini 2024 08 13 xAI

37.7

Rank #198 Confirmed

MiniMax-M2.5 MiniMax

38.3

Rank #188 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Grok 2 Mini 2024 08 13 scores higher in 3 categories and MiniMax-M2.5 in 5 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in coding, where MiniMax-M2.5 leads 48.1 to 37.0.
  • MiniMax-M2.5 has downloadable open weights; the other is API-only.

Side by side

Grok 2 Mini 2024 08 13 and MiniMax-M2.5 specifications
Grok 2 Mini 2024 08 13MiniMax-M2.5
ProviderxAIMiniMax
Noometry Index37.738.3
Released2024-08-132026-02-12
WeightsProprietaryOpen
Context window—205K
Max output—131K
Input $ / M tokens—$0.30
Output $ / M tokens—$1.20
Results tracked1733

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

Category by category

Coding MiniMax-M2.5 leads

Grok 2 Mini 2024 08 13: 37.0 (#199), MiniMax-M2.5: 48.1 (#58)

Coding benchmarks
BenchmarkGrok 2 Mini 2024 08 13MiniMax-M2.5
LMArena Coding12691381
SWE-bench Verified (bash only)—75.8%
LMArena WebDev—1387
SWE-bench Multilingual—68.3%
ALE-Bench—618.17

Agentic & Tool Use Not comparable

Grok 2 Mini 2024 08 13: —, MiniMax-M2.5: 30.4 (#77)

Agentic & Tool Use benchmarks
BenchmarkGrok 2 Mini 2024 08 13MiniMax-M2.5
Terminal-Bench—42.7%
Vending-Bench 2—-23.16

Reasoning Grok 2 Mini 2024 08 13 leads

Grok 2 Mini 2024 08 13: 24.8 (#159), MiniMax-M2.5: 17.5 (#292)

Reasoning benchmarks
BenchmarkGrok 2 Mini 2024 08 13MiniMax-M2.5
LMArena Hard Prompts12551372
ARC-AGI-2—4.9%
Kagi LLM Benchmark—55.2%
NYT Connections (extended)—16.8%
ARC-AGI-1—63.7%
Epoch Capabilities Index—146.68

Math Grok 2 Mini 2024 08 13 leads

Grok 2 Mini 2024 08 13: 35.4 (#185), MiniMax-M2.5: 26.9 (#253)

Math benchmarks
BenchmarkGrok 2 Mini 2024 08 13MiniMax-M2.5
LMArena Math12651378
ProofBench—4%

Knowledge MiniMax-M2.5 leads

Grok 2 Mini 2024 08 13: 33.9 (#200), MiniMax-M2.5: 39.2 (#135)

Knowledge benchmarks
BenchmarkGrok 2 Mini 2024 08 13MiniMax-M2.5
LMArena Expert12381379
Vectara Hallucination Rate—9.1%

Multilingual MiniMax-M2.5 leads

Grok 2 Mini 2024 08 13: 41.4 (#208), MiniMax-M2.5: 47.1 (#152)

Multilingual benchmarks
BenchmarkGrok 2 Mini 2024 08 13MiniMax-M2.5
LMArena Non-English12571338
LMArena Chinese12621393
LMArena French12861362
LMArena German12731362
LMArena Japanese12131171
LMArena Korean11951232
LMArena Russian12611358
LMArena Spanish12791354

Instruction Following MiniMax-M2.5 leads

Grok 2 Mini 2024 08 13: 65.5 (#220), MiniMax-M2.5: 71.5 (#148)

Instruction Following benchmarks
BenchmarkGrok 2 Mini 2024 08 13MiniMax-M2.5
LMArena Instruction Following12451353

Long Context Too close to call

Grok 2 Mini 2024 08 13: 38.4 (#196), MiniMax-M2.5: 37.5 (#216)

Long Context benchmarks
BenchmarkGrok 2 Mini 2024 08 13MiniMax-M2.5
LMArena Longer Query12661366
CL-bench—11.4%
CL-bench Life—6.3%

Writing & Preference MiniMax-M2.5 leads

Grok 2 Mini 2024 08 13: 47.3 (#211), MiniMax-M2.5: 53.9 (#153)

Writing & Preference benchmarks
BenchmarkGrok 2 Mini 2024 08 13MiniMax-M2.5
LMArena Text12811359
LMArena Creative Writing12421331
LMArena Multi-Turn12651364
EQ-Bench Creative Writing—1361

Frequently asked questions

Is Grok 2 Mini 2024 08 13 better than MiniMax-M2.5?

Grok 2 Mini 2024 08 13 and MiniMax-M2.5 score almost the same on the Noometry Index (37.7 vs 38.3), so choose on price, context window or the category you care about most.

Is Grok 2 Mini 2024 08 13 or MiniMax-M2.5 better for coding?

MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 37.0 in the Noometry coding category.

How many benchmarks do Grok 2 Mini 2024 08 13 and MiniMax-M2.5 share?

17 benchmarks have published results for both models. Grok 2 Mini 2024 08 13 has 17 scored results on Noometry and MiniMax-M2.5 has 33.

Related comparisons

Go deeper