MiniMax M2.1 vs Hy3 preview
Hy3 preview leads MiniMax M2.1 on the Artificial Analysis Intelligence Index, 25.3 to 20.9, and Hy3 preview costs 2.0x less per output token ($0.60 vs $1.20 per million). Updated October 22, 2026; 7 benchmarks have a result for both.
MiniMax M2.1 or Hy3 preview: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick MiniMax M2.1 for work measured by Terminal-Bench Hard (Artificial Analysis run) or AA Intelligence Index, where it leads.
- Shared results
- 7
- MiniMax M2.1 only
- 27
- Hy3 preview only
- 29
- Like-for-like categories
- 5 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.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
Hy3 preview
Hy3 preview leads, 25.3 against 20.9.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Hy3 preview has a AA Agentic Index result, 24.1.
Directional only
Reasoning
GPQA Diamond
No call
Only MiniMax M2.1 has a GPQA Diamond result, 78.5%.
Directional only
Math
AIME
No call
Only MiniMax M2.1 has a AIME result, 77.9%.
Directional only
Knowledge
MMLU Pro
No call
Only MiniMax M2.1 has a MMLU Pro result, 87.0%.
Directional only
Web design
Design Arena: websites
No call
Only MiniMax M2.1 has a Design Arena: websites result, 1201.
Directional only
Long documents
Listed context window
Hy3 preview
Hy3 preview takes 262K tokens against 205K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Hy3 preview
MiniMax M2.1 $0.0009, Hy3 preview $0.0005 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only MiniMax M2.1 has the number, $0.59.
Directional only
At a glance
- Coding index
- MiniMax M2.1 not benchmarked, Hy3 preview not benchmarked.
- Widest category
- Agentic work, 7.3 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: MiniMax M2.1 85.4% against Hy3 preview 92.7%, 7.3 points apart on a 0 to 100 scale.
- Output price
- MiniMax M2.1 $1.20 against Hy3 preview $0.60 per million output tokens, 2.0x apart.
- Context window
- MiniMax M2.1 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.
| Category | MiniMax M2.1 | Bars | Hy3 preview | Ties |
|---|---|---|---|---|
| Coding | 0 | 1 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 0 | 2 | ||
| General | 2 | 0 | ||
| All shared boards | 2 | 5 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index01
| Benchmark | MiniMax M2.1 | Hy3 preview | Leader |
|---|---|---|---|
| LMArena WebDev | Not measured | 1357 | Only Hy3 preview measured |
| AA Coding Index | Not measured | 58.8 | Only Hy3 preview measured |
| LiveCodeBench (Vals AI) | 81.8% | Not measured | Only MiniMax M2.1 measured |
| SWE-bench Verified (Vals AI) | 74.8% | Not measured | Only MiniMax M2.1 measured |
| LiveCodeBench (Artificial Analysis run) | 81.0% | Not measured | Only MiniMax M2.1 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 28.8% | 34.1% | Hy3 preview |
| Terminal-Bench | 36.6% | Not measured | Only MiniMax M2.1 measured |
| ALE-Bench | 623.8 | Not measured | Only MiniMax M2.1 measured |
| LMArena Text: coding | Not measured | 1421 | Only Hy3 preview measured |
| LMArena Text: software and IT | Not measured | 1423 | Only Hy3 preview measured |
| LMArena WebDev: React | Not measured | 1349 | Only Hy3 preview measured |
| LMArena WebDev: HTML | Not measured | 1356 | Only Hy3 preview measured |
| Neither model has a result on the other 31 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | MiniMax M2.1 | Hy3 preview | Leader |
|---|---|---|---|
| AA Intelligence Index | 20.9 | 25.3 | Hy3 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
| Benchmark | MiniMax M2.1 | Hy3 preview | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 24.1 | Only Hy3 preview measured |
| τ²-Bench Telecom | 85.4% | 92.7% | Hy3 preview |
| Neither model has a result on the other 40 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | MiniMax M2.1 | Hy3 preview | Leader |
|---|---|---|---|
| GPQA Diamond | 78.5% | Not measured | Only MiniMax M2.1 measured |
| GPQA Diamond (Artificial Analysis run) | 83.0% | 86.7% | Hy3 preview |
| Humanity's Last Exam (Artificial Analysis run) | 23.2% | 27.8% | Hy3 preview |
| LMArena Text: hard prompts | Not measured | 1413 | Only Hy3 preview measured |
| LMArena Text: expert | Not measured | 1422 | Only Hy3 preview measured |
| LMArena Text: hard prompts in English | Not measured | 1416 | Only Hy3 preview measured |
| Neither model has a result on the other 17 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | MiniMax M2.1 | Hy3 preview | Leader |
|---|---|---|---|
| AIME | 77.9% | Not measured | Only MiniMax M2.1 measured |
| MATH 500 (Vals AI) | 89.0% | Not measured | Only MiniMax M2.1 measured |
| MGSM (Vals AI) | 87.8% | Not measured | Only MiniMax M2.1 measured |
| AA Math Index | 82.7 | Not measured | Only MiniMax M2.1 measured |
| AIME 2025 (Artificial Analysis run) | 82.7% | Not measured | Only MiniMax M2.1 measured |
| LMArena Text: math | Not measured | 1424 | Only Hy3 preview measured |
| LMArena Text: mathematical work | Not measured | 1442 | Only Hy3 preview measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index12 boards, none shared
| Benchmark | MiniMax M2.1 | Hy3 preview | Leader |
|---|---|---|---|
| MMLU Pro | 87.0% | Not measured | Only MiniMax M2.1 measured |
| LegalBench (Vals AI) | 75.5% | Not measured | Only MiniMax M2.1 measured |
| CaseLaw (Vals AI) | 55.8% | Not measured | Only MiniMax M2.1 measured |
| CorpFin (Vals AI) | 58.9% | Not measured | Only MiniMax M2.1 measured |
| TaxEval (Vals AI) | 66.3% | Not measured | Only MiniMax M2.1 measured |
| MedQA (Vals AI) | 91.2% | Not measured | Only MiniMax M2.1 measured |
| MedCode (Vals AI) | 34.1% | Not measured | Only MiniMax M2.1 measured |
| MMLU Pro (Artificial Analysis run) | 87.5% | Not measured | Only MiniMax M2.1 measured |
| LMArena Text: science | Not measured | 1416 | Only Hy3 preview measured |
| LMArena Text: medicine and healthcare | Not measured | 1405 | Only Hy3 preview measured |
| LMArena Text: legal and government | Not measured | 1430 | Only Hy3 preview measured |
| LMArena Text: business and finance | Not measured | 1397 | Only Hy3 preview measured |
| 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
| Benchmark | MiniMax M2.1 | Hy3 preview | Leader |
|---|---|---|---|
| Design Arena: websites | 1201 | Not measured | Only MiniMax M2.1 measured |
| Design Arena: UI components | 1220 | Not measured | Only MiniMax M2.1 measured |
| Design Arena: game dev | 1134 | Not measured | Only MiniMax M2.1 measured |
| Design Arena: data viz | 1206 | Not measured | Only MiniMax M2.1 measured |
| Design Arena: 3D | 1164 | Not measured | Only MiniMax M2.1 measured |
| Design Arena: all code categories | 1190 | Not measured | Only MiniMax M2.1 measured |
| Design Arena: SVG | 1131 | Not measured | Only MiniMax M2.1 measured |
| Neither model has a result on the other 2 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | MiniMax M2.1 | Hy3 preview | Leader |
|---|---|---|---|
| MedScribe (Vals AI) | 80.8% | Not measured | Only MiniMax M2.1 measured |
| IFBench | 69.9% | 63.1% | MiniMax M2.1 |
| Long context reasoning (AA-LCR) | 67.7% | 64.7% | MiniMax M2.1 |
| LMArena Text | Not measured | 1401 | Only Hy3 preview measured |
| LMArena Text: instruction following | Not measured | 1383 | Only Hy3 preview measured |
| LMArena Text: creative writing | Not measured | 1339 | Only Hy3 preview measured |
| LMArena Text: English | Not measured | 1409 | Only Hy3 preview measured |
| LMArena Text: non-English | Not measured | 1390 | Only Hy3 preview measured |
| LMArena Text: Chinese | Not measured | 1435 | Only Hy3 preview measured |
| LMArena Text: French | Not measured | 1425 | Only Hy3 preview measured |
| LMArena Text: Spanish | Not measured | 1399 | Only Hy3 preview measured |
| LMArena Text: Russian | Not measured | 1399 | Only Hy3 preview measured |
| LMArena Text: multi-turn | Not measured | 1411 | Only Hy3 preview measured |
| LMArena Text: longer queries | Not measured | 1402 | Only Hy3 preview measured |
| LMArena Text: writing and language | Not measured | 1370 | Only Hy3 preview measured |
| LMArena Text: entertainment and media | Not measured | 1352 | Only Hy3 preview measured |
| Neither model has a result on the other 32 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | MiniMax M2.1 | Hy3 preview | Leader |
|---|---|---|---|
| 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
Hy3 preview costs less
Repository review
50K input + 3K output tokens
Hy3 preview costs less
Agent loop
200K input + 10K output tokens
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.
| Specification | MiniMax M2.1 | Tencent Hy3 preview |
|---|---|---|
| Maker | MiniMax | Tencent |
| Weights | Open weights | Open weights |
| Released | December 23, 2025 | April 22, 2026 |
| Context window | 205K | 262K |
| Input $/Mtok | $0.30 | $0.18 |
| Output $/Mtok | $1.20 | $0.60 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | $0.59 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is MiniMax M2.1 better than Hy3 preview for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick MiniMax M2.1 for work measured by Terminal-Bench Hard (Artificial Analysis run) or AA Intelligence Index, where it leads.
Which is cheaper, MiniMax M2.1 or Hy3 preview?
MiniMax M2.1 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 M2.1 only.
Which has the bigger context window, MiniMax M2.1 or Hy3 preview?
Hy3 preview, with 262K tokens against 205K.
How many benchmarks is the MiniMax M2.1 vs Hy3 preview comparison based on?
7 benchmarks have a result for both models as of October 22, 2026. MiniMax M2.1's coding index rests on 1 independent benchmark and Hy3 preview's on 1. Where only one model has a result, the page says so instead of naming a winner.