Enter opens the highlighted result. Esc closes.

MiniMax M2 vs Mistral Large

MiniMax M2 leads Mistral Large on the Artificial Analysis Intelligence Index, 18.6 to 5.8, and MiniMax M2 costs 5.9x less per output token ($1.02 vs $6.00 per million). Updated October 21, 2026; 31 benchmarks have a result for both.

Replace MiniMax M2 Replace Mistral Large
MiniMax M2MiniMax
Coding
No data
Overall
No data
Output $/M
$1.02
31
Mistral LargeMistral AI
Coding
No data
Overall
No data
Output $/M
$6.00
0
vs boards won of 31 shared

MiniMax M2 or Mistral Large: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick MiniMax M2 for output tokens 5.9x cheaper ($1.02 vs $6.00 per million) and a larger context window (205K against 128K tokens).

Model AMiniMax M2MiniMaxNot benchmarked1 independent benchmark$0.702 per solved taskModel BMistral LargeMistral AINot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
31
MiniMax M2 only
19
Mistral Large only
13
Like-for-like categories
6 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
MiniMax M2 not benchmarked, Mistral Large not benchmarked.
Widest category
Coding, 32.4 points apart on average over 3 shared benchmarks.
Widest single gap
LiveCodeBench (Artificial Analysis run): MiniMax M2 82.6% against Mistral Large 17.8%, 64.8 points apart on a 0 to 100 scale.
Output price
MiniMax M2 $1.02 against Mistral Large $6.00 per million output tokens, 5.9x apart.
Context window
MiniMax M2 takes 205K tokens, Mistral Large 128K.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryMiniMax M2BarsMistral LargeTies
Coding30
Intelligence10
Reasoning50
Math20
Knowledge50
General150
All shared boards310
CodingLike-for-likeSix of these boards feed the Vibe Coding Index30
Coding benchmarks for MiniMax M2 and Mistral Large
BenchmarkMiniMax M2Mistral LargeLeader
SWE-bench Verified61.0%Not measuredOnly MiniMax M2 measured
LMArena WebDev1297Not measuredOnly MiniMax M2 measured
LiveCodeBench (Vals AI)Not measured37.1%Only Mistral Large measured
LiveCodeBench (Artificial Analysis run)82.6%17.8%MiniMax M2
Terminal-Bench Hard (Artificial Analysis run)25.8%Not measuredOnly MiniMax M2 measured
Terminal-Bench30.0%Not measuredOnly MiniMax M2 measured
LMArena Text: coding13711275MiniMax M2
LMArena Text: software and IT13731274MiniMax M2
LMArena WebDev: HTML1306Not measuredOnly MiniMax M2 measured
Neither model has a result on the other 30 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for MiniMax M2 and Mistral Large
BenchmarkMiniMax M2Mistral LargeLeader
AA Intelligence Index18.65.8MiniMax M2
Epoch Capabilities IndexNot measured122.1Only Mistral Large measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Agentic work benchmarks for MiniMax M2 and Mistral Large
BenchmarkMiniMax M2Mistral LargeLeader
τ²-Bench Telecom86.8%Not measuredOnly MiniMax M2 measured
Vending-Bench 2$161Not measuredOnly MiniMax M2 measured
Neither model has a result on the other 39 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
Reasoning benchmarks for MiniMax M2 and Mistral Large
BenchmarkMiniMax M2Mistral LargeLeader
GPQA DiamondNot measured47.7%Only Mistral Large measured
GPQA Diamond (Artificial Analysis run)77.7%35.1%MiniMax M2
Humanity's Last Exam (Artificial Analysis run)13.7%3.5%MiniMax M2
LMArena Text: hard prompts13571257MiniMax M2
LMArena Text: expert13381208MiniMax M2
LMArena Text: hard prompts in English13761268MiniMax M2
Kagi LLM Benchmark57.8%Not measuredOnly MiniMax M2 measured
Neither model has a result on the other 15 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for MiniMax M2 and Mistral Large
BenchmarkMiniMax M2Mistral LargeLeader
AIMENot measured9.2%Only Mistral Large measured
MATH 500 (Vals AI)Not measured74.4%Only Mistral Large measured
MGSM (Vals AI)Not measured87.2%Only Mistral Large measured
AA Math Index78.3Not measuredOnly MiniMax M2 measured
AIME 2025 (Artificial Analysis run)78.3%Not measuredOnly MiniMax M2 measured
LMArena Text: math13511261MiniMax M2
LMArena Text: mathematical work13681257MiniMax M2
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
Knowledge benchmarks for MiniMax M2 and Mistral Large
BenchmarkMiniMax M2Mistral LargeLeader
MMLU ProNot measured69.7%Only Mistral Large measured
TaxEval (Vals AI)Not measured63.8%Only Mistral Large measured
MedQA (Vals AI)Not measured76.2%Only Mistral Large measured
MMLU Pro (Artificial Analysis run)82.0%51.5%MiniMax M2
MMLUNot measured68.8%Only Mistral Large measured
LMArena Text: science13481260MiniMax M2
LMArena Text: medicine and healthcare13671255MiniMax M2
LMArena Text: legal and government13491275MiniMax M2
LMArena Text: business and finance13361238MiniMax M2
Neither model has a result on the other 9 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Web design benchmarks for MiniMax M2 and Mistral Large
BenchmarkMiniMax M2Mistral LargeLeader
Design Arena: websites1143Not measuredOnly MiniMax M2 measured
Design Arena: UI components1136Not measuredOnly MiniMax M2 measured
Design Arena: game dev1118Not measuredOnly MiniMax M2 measured
Design Arena: data viz1140Not measuredOnly MiniMax M2 measured
Design Arena: 3D1098Not measuredOnly MiniMax M2 measured
Design Arena: all code categories1135Not measuredOnly MiniMax M2 measured
Design Arena: SVG1100Not measuredOnly MiniMax M2 measured
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index150
General benchmarks for MiniMax M2 and Mistral Large
BenchmarkMiniMax M2Mistral LargeLeader
IFBench72.3%Not measuredOnly MiniMax M2 measured
Long context reasoning (AA-LCR)64.3%Not measuredOnly MiniMax M2 measured
DTBenchNot measured60.8%Only Mistral Large measured
LMArena Text13401265MiniMax M2
LMArena Text: instruction following13291249MiniMax M2
LMArena Text: creative writing12861242MiniMax M2
LMArena Text: English13641284MiniMax M2
LMArena Text: non-English13131235MiniMax M2
LMArena Text: Chinese13661239MiniMax M2
LMArena Text: German13571242MiniMax M2
LMArena Text: JapaneseNot measured1170Only Mistral Large measured
LMArena Text: KoreanNot measured1202Only Mistral Large measured
LMArena Text: French13361325MiniMax M2
LMArena Text: Spanish13261268MiniMax M2
LMArena Text: Russian13301252MiniMax M2
LMArena Text: Polish13121157MiniMax M2
LMArena Text: multi-turn13611260MiniMax M2
LMArena Text: longer queries13311261MiniMax M2
LMArena Text: writing and language12951261MiniMax M2
LMArena Text: entertainment and media12981230MiniMax M2
Neither model has a result on the other 26 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for MiniMax M2 and Mistral Large
BenchmarkMiniMax M2Mistral LargeLeader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

MiniMax M2$0.0008Fits in one request
Mistral Large$0.0050Fits in one request

MiniMax M2 costs less

Repository review

50K input + 3K output tokens

MiniMax M2$0.016Fits in one request
Mistral Large$0.118Fits in one request

MiniMax M2 costs less

Agent loop

200K input + 10K output tokens

MiniMax M2$0.061Exceeds the context window
Mistral Large$0.460Exceeds the context window

MiniMax M2 costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of MiniMax M2 and Mistral Large
SpecificationMiniMax M2Mistral Large
MakerMiniMaxMistral AI
WeightsOpen weightsNo public weights listed
ReleasedOctober 23, 2025February 26, 2024
Context window205K128K
Input $/Mtok$0.255$2.00
Output $/Mtok$1.02$6.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it10
Cost per solved task$0.702Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is MiniMax M2 better than Mistral Large for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick MiniMax M2 for output tokens 5.9x cheaper ($1.02 vs $6.00 per million) and a larger context window (205K against 128K tokens).

Which is cheaper, MiniMax M2 or Mistral Large?

MiniMax M2 costs $0.255 per million input tokens and $1.02 per million output tokens; Mistral Large costs $2.00 and $6.00. Cost per solved task is known for MiniMax M2 only.

Which has the bigger context window, MiniMax M2 or Mistral Large?

MiniMax M2, with 205K tokens against 128K.

How many benchmarks is the MiniMax M2 vs Mistral Large comparison based on?

31 benchmarks have a result for both models as of October 21, 2026. MiniMax M2's coding index rests on 1 independent benchmark and Mistral Large's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next