Model comparison

MiniMax-M2 vs Ministral 8B

MiniMax-M2 is the stronger model overall, scoring 37.4 to 28.2 on the Noometry Index. Ministral 8B costs 3.5× less per token, which makes it the better buy when MiniMax-M2's lead doesn't matter for your workload.

Last verified . 12 shared benchmarks.

MiniMax-M2 MiniMax

37.4

Rank #204 Confirmed

Ministral 8B Mistral AI

28.2

Rank #325 Confirmed

Summary

  • They share 12 benchmarks with published results for both. MiniMax-M2 scores higher in 9 categories and Ministral 8B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where MiniMax-M2 leads 37.0 to 12.6.
  • Ministral 8B is cheaper at $0.15 / $0.15 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.
  • Ministral 8B accepts more context: 262K tokens versus 205K.

Side by side

MiniMax-M2 and Ministral 8B specifications
MiniMax-M2Ministral 8B
ProviderMiniMaxMistral AI
Noometry Index37.428.2
Released2025-10-272024-10-01
WeightsOpenOpen
Context window205K262K
Max output131K262K
Input $ / M tokens$0.30$0.15
Output $ / M tokens$1.20$0.15
Results tracked2117

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

Category by category

Coding MiniMax-M2 leads

MiniMax-M2: 39.3 (#159), Ministral 8B: 35.0 (#230)

Coding benchmarks
BenchmarkMiniMax-M2Ministral 8B
LMArena Coding13701202
SWE-bench Verified (bash only)61%—
LMArena WebDev1297—

Agentic & Tool Use MiniMax-M2 leads

MiniMax-M2: 25.1 (#109), Ministral 8B: 16.4 (#148)

Agentic & Tool Use benchmarks
BenchmarkMiniMax-M2Ministral 8B
Terminal-Bench30%—
Berkeley Function Calling Leaderboard—11.1%
Vending-Bench 2160.6—

Reasoning Too close to call

MiniMax-M2: 19.4 (#258), Ministral 8B: 18.4 (#281)

Reasoning benchmarks
BenchmarkMiniMax-M2Ministral 8B
LMArena Hard Prompts13571191
Kagi LLM Benchmark57.8%—
NYT Connections (extended)14.8%—
DTBench—45.7%

Math MiniMax-M2 leads

MiniMax-M2: 37.3 (#160), Ministral 8B: 25.7 (#267)

Math benchmarks
BenchmarkMiniMax-M2Ministral 8B
LMArena Math13521188
MATH Level 5—14.9%

Knowledge MiniMax-M2 leads

MiniMax-M2: 37.0 (#163), Ministral 8B: 12.6 (#297)

Knowledge benchmarks
BenchmarkMiniMax-M2Ministral 8B
LMArena Expert13371170
GPQA Diamond—27.1%
Vectara Hallucination Rate—7.4%

Multilingual MiniMax-M2 leads

MiniMax-M2: 45.3 (#171), Ministral 8B: 35.1 (#247)

Multilingual benchmarks
BenchmarkMiniMax-M2Ministral 8B
LMArena Non-English13131165
LMArena Chinese13661193
LMArena Russian13311195
LMArena French1335—
LMArena German1355—
LMArena Spanish1326—

Instruction Following MiniMax-M2 leads

MiniMax-M2: 70.2 (#166), Ministral 8B: 60.5 (#250)

Instruction Following benchmarks
BenchmarkMiniMax-M2Ministral 8B
LMArena Instruction Following13281161

Long Context MiniMax-M2 leads

MiniMax-M2: 40.5 (#153), Ministral 8B: 36.7 (#227)

Long Context benchmarks
BenchmarkMiniMax-M2Ministral 8B
LMArena Longer Query13311212

Writing & Preference MiniMax-M2 leads

MiniMax-M2: 53.0 (#162), Ministral 8B: 39.6 (#246)

Writing & Preference benchmarks
BenchmarkMiniMax-M2Ministral 8B
LMArena Text13401191
LMArena Creative Writing12861175
LMArena Multi-Turn13611166

Frequently asked questions

Is MiniMax-M2 better than Ministral 8B?

MiniMax-M2 is the stronger model overall, scoring 37.4 to 28.2 on the Noometry Index. Ministral 8B costs 3.5× less per token, which makes it the better buy when MiniMax-M2's lead doesn't matter for your workload.

Which is cheaper, MiniMax-M2 or Ministral 8B?

Ministral 8B is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; MiniMax-M2 lists at $0.30 and $1.20.

Is MiniMax-M2 or Ministral 8B better for coding?

MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 35.0 in the Noometry coding category.

Which has the bigger context window?

Ministral 8B does, with 262K tokens against 205K.

How many benchmarks do MiniMax-M2 and Ministral 8B share?

12 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and Ministral 8B has 17.

Related comparisons

Go deeper