Enter opens the highlighted result. Esc closes.

MiniMax M2.5 vs Hy3 preview

Hy3 preview leads MiniMax M2.5 on the Artificial Analysis Intelligence Index, 25.3 to 22.8, and Hy3 preview costs 2.0x less per output token ($0.60 vs $1.20 per million). Updated October 22, 2026; 34 benchmarks have a result for both.

Replace MiniMax M2.5 Replace Hy3 preview
MiniMax M2.5MiniMax
Coding
37.2
Overall
37.3
Output $/M
$1.20
7
Hy3 previewTencent
Coding
No data
Overall
No data
Output $/M
$0.60
27
vs boards won of 34 shared

MiniMax M2.5 or Hy3 preview: which to pick

Only MiniMax M2.5 has a coding score, 37.2 on the Vibe Coding Index; Hy3 preview has none, so the two cannot be ranked on coding.

Pick Hy3 preview for output tokens 2.0x cheaper ($0.60 vs $1.20 per million) and a larger context window (262K against 205K tokens).

Model AMiniMax M2.5MiniMax37.2/1003 independent benchmarks$0.62 per solved taskModel BHy3 previewTencentNot benchmarked1 independent benchmarkNo cost per solved task
Shared results
34
MiniMax M2.5 only
34
Hy3 preview only
2
Like-for-like categories
7 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 M2.5 37.2 from 3 benchmarks, Hy3 preview not benchmarked.
Widest category
Math, 9.1 points apart on average over 2 shared benchmarks.
Widest single gap
LMArena Text: legal and government: MiniMax M2.5 1366 against Hy3 preview 1430, 10.7 points apart on a 0 to 100 scale.
Output price
MiniMax M2.5 $1.20 against Hy3 preview $0.60 per million output tokens, 2.0x apart.
Context window
MiniMax M2.5 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 M2.5BarsHy3 previewTies
Coding42
Intelligence01
Agentic work10
Reasoning05
Math02
Knowledge04
General213
All shared boards727
CodingLike-for-likeSix of these boards feed the Vibe Coding Index42
Coding benchmarks for MiniMax M2.5 and Hy3 preview
BenchmarkMiniMax M2.5Hy3 previewLeader
SWE-bench Verified75.8%Not measuredOnly MiniMax M2.5 measured
SWE-bench Multilingual68.3%Not measuredOnly MiniMax M2.5 measured
LMArena WebDev13861357MiniMax M2.5
AA Coding IndexNot measured58.8Only Hy3 preview measured
LiveCodeBench (Vals AI)79.2%Not measuredOnly MiniMax M2.5 measured
SWE-bench Verified (Vals AI)74.2%Not measuredOnly MiniMax M2.5 measured
Vibe Code Bench (Vals AI)14.8%Not measuredOnly MiniMax M2.5 measured
Terminal-Bench Hard (Artificial Analysis run)34.8%34.1%MiniMax M2.5
Terminal-Bench42.7%Not measuredOnly MiniMax M2.5 measured
ALE-Bench618.2Not measuredOnly MiniMax M2.5 measured
LMArena Text: coding13801421Hy3 preview
LMArena Text: software and IT13831423Hy3 preview
LMArena WebDev: React13741349MiniMax M2.5
LMArena WebDev: HTML14141356MiniMax M2.5
Neither model has a result on the other 25 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for MiniMax M2.5 and Hy3 preview
BenchmarkMiniMax M2.5Hy3 previewLeader
AA Intelligence Index22.825.3Hy3 preview
Epoch Capabilities Index146.6Not measuredOnly MiniMax M2.5 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for MiniMax M2.5 and Hy3 preview
BenchmarkMiniMax M2.5Hy3 previewLeader
AA Agentic IndexNot measured24.1Only Hy3 preview measured
τ²-Bench Telecom95.3%92.7%MiniMax M2.5
Vending-Bench 2-$23Not measuredOnly MiniMax M2.5 measured
Neither model has a result on the other 38 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
Reasoning benchmarks for MiniMax M2.5 and Hy3 preview
BenchmarkMiniMax M2.5Hy3 previewLeader
GPQA Diamond82.1%Not measuredOnly MiniMax M2.5 measured
GPQA Diamond (Artificial Analysis run)84.8%86.7%Hy3 preview
Humanity's Last Exam (Artificial Analysis run)20.5%27.8%Hy3 preview
ARC-AGI63.7%Not measuredOnly MiniMax M2.5 measured
ARC-AGI-24.9%Not measuredOnly MiniMax M2.5 measured
LMArena Text: hard prompts13721413Hy3 preview
LMArena Text: expert13781422Hy3 preview
LMArena Text: hard prompts in English13841416Hy3 preview
Kagi LLM Benchmark55.2%Not measuredOnly MiniMax M2.5 measured
Neither model has a result on the other 13 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for MiniMax M2.5 and Hy3 preview
BenchmarkMiniMax M2.5Hy3 previewLeader
AIME88.8%Not measuredOnly MiniMax M2.5 measured
ProofBench4.0%Not measuredOnly MiniMax M2.5 measured
LMArena Text: math13781424Hy3 preview
LMArena Text: mathematical work13781442Hy3 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 M2.5 and Hy3 preview
BenchmarkMiniMax M2.5Hy3 previewLeader
MMLU Pro80.1%Not measuredOnly MiniMax M2.5 measured
LegalBench (Vals AI)80.0%Not measuredOnly MiniMax M2.5 measured
CaseLaw (Vals AI)53.5%Not measuredOnly MiniMax M2.5 measured
CorpFin (Vals AI)59.6%Not measuredOnly MiniMax M2.5 measured
TaxEval (Vals AI)68.2%Not measuredOnly MiniMax M2.5 measured
MedQA (Vals AI)92.5%Not measuredOnly MiniMax M2.5 measured
LMArena Text: science13691416Hy3 preview
LMArena Text: medicine and healthcare13571405Hy3 preview
LMArena Text: legal and government13661430Hy3 preview
LMArena Text: business and finance13561397Hy3 preview
Neither model has a result on the other 8 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Web design benchmarks for MiniMax M2.5 and Hy3 preview
BenchmarkMiniMax M2.5Hy3 previewLeader
Design Arena: websites1222Not measuredOnly MiniMax M2.5 measured
Design Arena: UI components1173Not measuredOnly MiniMax M2.5 measured
Design Arena: game dev1176Not measuredOnly MiniMax M2.5 measured
Design Arena: data viz1172Not measuredOnly MiniMax M2.5 measured
Design Arena: 3D1170Not measuredOnly MiniMax M2.5 measured
Design Arena: all code categories1207Not measuredOnly MiniMax M2.5 measured
Design Arena: SVG1150Not measuredOnly MiniMax M2.5 measured
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index213
General benchmarks for MiniMax M2.5 and Hy3 preview
BenchmarkMiniMax M2.5Hy3 previewLeader
IFBench71.6%63.1%MiniMax M2.5
Long context reasoning (AA-LCR)73.3%64.7%MiniMax M2.5
CL-bench11.4%Not measuredOnly MiniMax M2.5 measured
CL-bench Life6.3%Not measuredOnly MiniMax M2.5 measured
LMArena Text13591401Hy3 preview
LMArena Text: instruction following13531383Hy3 preview
LMArena Text: creative writing13311339Hy3 preview
LMArena Text: English13801409Hy3 preview
LMArena Text: non-English13381390Hy3 preview
LMArena Text: Chinese13931435Hy3 preview
LMArena Text: German1361Not measuredOnly MiniMax M2.5 measured
LMArena Text: Japanese1171Not measuredOnly MiniMax M2.5 measured
LMArena Text: Korean1233Not measuredOnly MiniMax M2.5 measured
LMArena Text: French13631425Hy3 preview
LMArena Text: Spanish13531399Hy3 preview
LMArena Text: Russian13591399Hy3 preview
LMArena Text: Polish1334Not measuredOnly MiniMax M2.5 measured
LMArena Text: multi-turn13641411Hy3 preview
LMArena Text: longer queries13661402Hy3 preview
LMArena Text: writing and language13451370Hy3 preview
LMArena Text: entertainment and media13291352Hy3 preview
Neither model has a result on the other 25 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for MiniMax M2.5 and Hy3 preview
BenchmarkMiniMax M2.5Hy3 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 M2.5$0.0009Fits in one request
Hy3 preview$0.0005Fits in one request

Hy3 preview costs less

Repository review

50K input + 3K output tokens

MiniMax M2.5$0.019Fits in one request
Hy3 preview$0.011Fits in one request

Hy3 preview costs less

Agent loop

200K input + 10K output tokens

MiniMax M2.5$0.072Exceeds 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 M2.5 and Hy3 preview
SpecificationMiniMax M2.5Tencent Hy3 preview
MakerMiniMaxTencent
WeightsOpen weightsOpen weights
ReleasedFebruary 12, 2026April 22, 2026
Context window205K262K
Input $/Mtok$0.30$0.18
Output $/Mtok$1.20$0.60
Coding index37.2Not benchmarked
Independent measurements behind it31
Cost per solved task$0.62Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is MiniMax M2.5 better than Hy3 preview for coding?

Only MiniMax M2.5 has a coding score, 37.2 on the Vibe Coding Index; Hy3 preview has none, so the two cannot be ranked on coding. Pick Hy3 preview for output tokens 2.0x cheaper ($0.60 vs $1.20 per million) and a larger context window (262K against 205K tokens).

Which is cheaper, MiniMax M2.5 or Hy3 preview?

MiniMax M2.5 costs $0.30 per million input tokens and $1.20 per million output tokens; Hy3 preview costs $0.18 and $0.60. Cost per solved task is known for MiniMax M2.5 only.

Which has the bigger context window, MiniMax M2.5 or Hy3 preview?

Hy3 preview, with 262K tokens against 205K.

How many benchmarks is the MiniMax M2.5 vs Hy3 preview comparison based on?

34 benchmarks have a result for both models as of October 22, 2026. MiniMax M2.5's coding index rests on 3 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