LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

MiniMax M2 vs Hy3 preview

Updated October 21, 2026. 33 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace MiniMax M2 Replace Hy3 preview
MiniMax M2MiniMax
Coding
45.3
Overall
18.6
Output $/M
$1.02
1
Hy3 previewTencent
Coding
22.4
Overall
25.3
Output $/M
$0.60
32
vs boards won of 33 shared

Decision reading

Pick MiniMax M2 for coding: it scores 45.3 on the Vibe Coding Index against 22.4 for Hy3 preview.

Pick Hy3 preview when output tokens cost 1.7x less, or when the context window is larger, 262K against 205K tokens.

Model AMiniMax M2MiniMax45.3/1002 independent benchmarks$0.702 per solved taskModel BHy3 previewTencent22.4/1001 independent benchmarkNo cost per solved task
Shared results
33
MiniMax M2 only
16
Hy3 preview only
3
Like-for-like categories
7 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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 45.3 from 2 benchmarks, Hy3 preview 22.4 from 1 benchmark.
Widest category
Math, 12.2 points apart on average over 2 shared benchmarks.
Widest single gap
LMArena Text: French: MiniMax M2 1336 against Hy3 preview 1425, 14.8 points apart on a 0 to 100 scale.
Output price
MiniMax M2 $1.02 against Hy3 preview $0.60 per million output tokens, 1.7x apart.
Context window
MiniMax M2 takes 205K tokens, Hy3 preview 262K.

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 M2BarsHy3 previewTies
Coding05
Intelligence01
Agentic work01
Reasoning05
Math02
Knowledge04
General114
All shared boards132
CodingLike-for-likeFour of these boards feed the Vibe Coding Index05
Coding benchmarks for MiniMax M2 and Hy3 preview
BenchmarkMiniMax M2Hy3 previewLeader
SWE-bench Verified61.0%Not measuredOnly MiniMax M2 measured
LMArena WebDev12971357Hy3 preview
AA Coding IndexNot measured58.8Only Hy3 preview measured
LiveCodeBench (Artificial Analysis run)82.6%Not measuredOnly MiniMax M2 measured
Terminal-Bench Hard (Artificial Analysis run)25.8%34.1%Hy3 preview
Terminal-Bench30.0%Not measuredOnly MiniMax M2 measured
LMArena Text: coding13711421Hy3 preview
LMArena Text: software and IT13731423Hy3 preview
LMArena WebDev: ReactNot measured1349Only Hy3 preview measured
LMArena WebDev: HTML13061356Hy3 preview
Neither model has a result on the other 28 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for MiniMax M2 and Hy3 preview
BenchmarkMiniMax M2Hy3 previewLeader
AA Intelligence Index18.625.3Hy3 preview
Neither model has a result on the other 1 board here
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for MiniMax M2 and Hy3 preview
BenchmarkMiniMax M2Hy3 previewLeader
AA Agentic IndexNot measured24.1Only Hy3 preview measured
τ²-Bench Telecom86.8%92.7%Hy3 preview
Vending-Bench 2$161Not measuredOnly MiniMax M2 measured
Neither model has a result on the other 36 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
Reasoning benchmarks for MiniMax M2 and Hy3 preview
BenchmarkMiniMax M2Hy3 previewLeader
GPQA Diamond (Artificial Analysis run)77.7%86.7%Hy3 preview
Humanity's Last Exam (Artificial Analysis run)13.7%27.8%Hy3 preview
LMArena Text: hard prompts13571413Hy3 preview
LMArena Text: expert13381422Hy3 preview
LMArena Text: hard prompts in English13761416Hy3 preview
Neither model has a result on the other 16 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for MiniMax M2 and Hy3 preview
BenchmarkMiniMax M2Hy3 previewLeader
AA Math Index78.3Not measuredOnly MiniMax M2 measured
AIME 2025 (Artificial Analysis run)78.3%Not measuredOnly MiniMax M2 measured
LMArena Text: math13511424Hy3 preview
LMArena Text: mathematical work13681442Hy3 preview
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for MiniMax M2 and Hy3 preview
BenchmarkMiniMax M2Hy3 previewLeader
MMLU Pro (Artificial Analysis run)82.0%Not measuredOnly MiniMax M2 measured
LMArena Text: science13481416Hy3 preview
LMArena Text: medicine and healthcare13671405Hy3 preview
LMArena Text: legal and government13491430Hy3 preview
LMArena Text: business and finance13361397Hy3 preview
Neither model has a result on the other 12 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Web design benchmarks for MiniMax M2 and Hy3 preview
BenchmarkMiniMax M2Hy3 previewLeader
Design Arena: websites1144Not measuredOnly MiniMax M2 measured
Design Arena: UI components1136Not measuredOnly MiniMax M2 measured
Design Arena: game dev1119Not 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: SVG1098Not 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 index114
General benchmarks for MiniMax M2 and Hy3 preview
BenchmarkMiniMax M2Hy3 previewLeader
IFBench72.3%63.1%MiniMax M2
Long context reasoning (AA-LCR)64.3%64.7%Hy3 preview
LMArena Text13401401Hy3 preview
LMArena Text: instruction following13291383Hy3 preview
LMArena Text: creative writing12861339Hy3 preview
LMArena Text: English13641409Hy3 preview
LMArena Text: non-English13131390Hy3 preview
LMArena Text: Chinese13661435Hy3 preview
LMArena Text: German1357Not measuredOnly MiniMax M2 measured
LMArena Text: French13361425Hy3 preview
LMArena Text: Spanish13261399Hy3 preview
LMArena Text: Russian13301399Hy3 preview
LMArena Text: Polish1312Not measuredOnly MiniMax M2 measured
LMArena Text: multi-turn13611411Hy3 preview
LMArena Text: longer queries13311402Hy3 preview
LMArena Text: writing and language12951370Hy3 preview
LMArena Text: entertainment and media12981352Hy3 preview
Neither model has a result on the other 29 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for MiniMax M2 and Hy3 preview
BenchmarkMiniMax M2Hy3 previewLeader
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
Hy3 preview$0.0005Fits in one request

Hy3 preview costs less

Repository review

50K input + 3K output tokens

MiniMax M2$0.016Fits in one request
Hy3 preview$0.011Fits in one request

Hy3 preview costs less

Agent loop

200K input + 10K output tokens

MiniMax M2$0.061Exceeds the context window
Hy3 preview$0.042Fits in one request

Hy3 preview 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 Hy3 preview
SpecificationMiniMax M2Tencent Hy3 preview
MakerMiniMaxTencent
WeightsOpen weightsOpen weights
ReleasedOctober 23, 2025April 22, 2026
Context window205K262K
Input $/Mtok$0.255$0.18
Output $/Mtok$1.02$0.60
Coding index45.322.4
Independent measurements behind it21
Cost per solved task$0.702Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is MiniMax M2 better than Hy3 preview for coding?

Pick MiniMax M2 for coding: it scores 45.3 on the Vibe Coding Index against 22.4 for Hy3 preview. Pick Hy3 preview when output tokens cost 1.7x less, or when the context window is larger, 262K against 205K tokens.

Which is cheaper, MiniMax M2 or Hy3 preview?

MiniMax M2 costs $0.255 per million input tokens and $1.02 per million output tokens; Hy3 preview costs $0.18 and $0.60. Cost per solved task is known for MiniMax M2 only.

Which has the bigger context window, MiniMax M2 or Hy3 preview?

Hy3 preview, with 262K tokens against 205K.

How many benchmarks is the MiniMax M2 vs Hy3 preview comparison based on?

33 benchmarks have a result for both models as of October 21, 2026. MiniMax M2's coding index rests on 2 independent benchmarks and Hy3 preview's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next