MiniMax M2.5 vs Hy4 preview
Hy4 preview leads MiniMax M2.5 on coding, 44.3 to 37.2 on the Vibe Coding Index, and MiniMax M2.5 costs 2.1x less per output token ($1.20 vs $2.501 per million). Updated October 22, 2026; 6 benchmarks have a result for both.
MiniMax M2.5 or Hy4 preview: which to pick
Pick Hy4 preview for coding: it scores 44.3 on the Vibe Coding Index against 37.2 for MiniMax M2.5.
Pick MiniMax M2.5 for output tokens 2.1x cheaper ($1.20 vs $2.501 per million).
- Shared results
- 6
- MiniMax M2.5 only
- 62
- Hy4 preview only
- 18
- Like-for-like categories
- 3 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
Hy4 preview
Hy4 preview scores 44.3 against 37.2.
3 benchmarks behind each score
Intelligence
AA Intelligence Index
No call
Only MiniMax M2.5 has a AA Intelligence Index result, 22.8.
Directional only
Reasoning
GPQA Diamond
No call
Only MiniMax M2.5 has a GPQA Diamond result, 82.1%.
Directional only
Math
AIME
No call
Only MiniMax M2.5 has a AIME result, 88.8%.
Directional only
Knowledge
MMLU Pro
No call
Only MiniMax M2.5 has a MMLU Pro result, 80.1%.
Directional only
Web design
Design Arena: websites
No call
Only MiniMax M2.5 has a Design Arena: websites result, 1222.
Directional only
General
Vals Index
No call
Only Hy4 preview has a Vals Index result, 53.2%.
Directional only
Long documents
Listed context window
Hy4 preview
Hy4 preview takes 1.05M tokens against 205K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiniMax M2.5
MiniMax M2.5 $0.0009, Hy4 preview $0.0021 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only MiniMax M2.5 has the number, $0.62.
Directional only
At a glance
- Coding index
- MiniMax M2.5 37.2 from 3 benchmarks, Hy4 preview 44.3 from 3 benchmarks.
- Widest category
- Math, 71.0 points apart on average over 1 shared benchmark.
- Widest single gap
- ProofBench: MiniMax M2.5 4.0% against Hy4 preview 75.0%, 71.0 points apart on a 0 to 100 scale.
- Output price
- MiniMax M2.5 $1.20 against Hy4 preview $2.501 per million output tokens, 2.1x apart.
- Context window
- MiniMax M2.5 takes 205K tokens, Hy4 preview 1.05M.
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 M2.5 | Bars | Hy4 preview | Ties |
|---|---|---|---|---|
| Coding | 0 | 4 | ||
| Math | 0 | 1 | ||
| Knowledge | 0 | 1 | ||
| All shared boards | 0 | 6 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
| Benchmark | MiniMax M2.5 | Hy4 preview | Leader |
|---|---|---|---|
| SWE-bench Verified | 75.8% | Not measured | Only MiniMax M2.5 measured |
| SWE-bench Multilingual | 68.3% | Not measured | Only MiniMax M2.5 measured |
| LMArena WebDev | 1386 | 1631 | Hy4 preview |
| LiveCodeBench (Vals AI) | 79.2% | Not measured | Only MiniMax M2.5 measured |
| SWE-bench Verified (Vals AI) | 74.2% | Not measured | Only MiniMax M2.5 measured |
| Terminal-Bench 4 (Vals AI) | Not measured | 8.1% | Only Hy4 preview measured |
| Vibe Code Bench (Vals AI) | 14.8% | 77.5% | Hy4 preview |
| Code migration (Vals AI) | Not measured | 47.4% | Only Hy4 preview measured |
| ProgramBench (Vals AI) | Not measured | 0.0% | Only Hy4 preview measured |
| IOI (Vals AI) | Not measured | 59.3% | Only Hy4 preview measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 55.1% | Only Hy4 preview measured |
| CyberBench (Vals AI) | Not measured | 65.4% | Only Hy4 preview measured |
| Terminal-Bench Hard (Artificial Analysis run) | 34.8% | Not measured | Only MiniMax M2.5 measured |
| Terminal-Bench | 42.7% | Not measured | Only MiniMax M2.5 measured |
| ALE-Bench | 618.2 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: coding | 1380 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: software and IT | 1383 | Not measured | Only MiniMax M2.5 measured |
| LMArena WebDev: React | 1374 | 1653 | Hy4 preview |
| LMArena WebDev: HTML | 1414 | 1620 | Hy4 preview |
| Neither model has a result on the other 20 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | MiniMax M2.5 | Hy4 preview | Leader |
|---|---|---|---|
| AA Intelligence Index | 22.8 | Not measured | Only MiniMax M2.5 measured |
| Epoch Capabilities Index | 146.6 | Not measured | Only MiniMax M2.5 measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index10 boards, none shared
| Benchmark | MiniMax M2.5 | Hy4 preview | Leader |
|---|---|---|---|
| SREBench (Vals AI) | Not measured | 2.3% | Only Hy4 preview measured |
| Finance Agent (Vals AI) | Not measured | 55.1% | Only Hy4 preview measured |
| Tax Agent Bench (Vals AI) | Not measured | 32.6% | Only Hy4 preview measured |
| Legal Research Bench (Vals AI) | Not measured | 45.2% | Only Hy4 preview measured |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 8.8% | Only Hy4 preview measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 58.1% | Only Hy4 preview measured |
| BioMysteryBench (Vals AI) | Not measured | 69.3% | Only Hy4 preview measured |
| Terminal-Bench-Science (Vals AI) | Not measured | 1.4% | Only Hy4 preview measured |
| τ²-Bench Telecom | 95.3% | Not measured | Only MiniMax M2.5 measured |
| Vending-Bench 2 | -$23 | Not measured | Only MiniMax M2.5 measured |
| Neither model has a result on the other 31 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | MiniMax M2.5 | Hy4 preview | Leader |
|---|---|---|---|
| GPQA Diamond | 82.1% | Not measured | Only MiniMax M2.5 measured |
| GPQA Diamond (Artificial Analysis run) | 84.8% | Not measured | Only MiniMax M2.5 measured |
| Humanity's Last Exam (Artificial Analysis run) | 20.5% | Not measured | Only MiniMax M2.5 measured |
| ARC-AGI | 63.7% | Not measured | Only MiniMax M2.5 measured |
| ARC-AGI-2 | 4.9% | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: hard prompts | 1372 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: expert | 1378 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: hard prompts in English | 1384 | Not measured | Only MiniMax M2.5 measured |
| Kagi LLM Benchmark | 55.2% | Not measured | Only 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 index01
| Benchmark | MiniMax M2.5 | Hy4 preview | Leader |
|---|---|---|---|
| AIME | 88.8% | Not measured | Only MiniMax M2.5 measured |
| ProofBench | 4.0% | 75.0% | Hy4 preview |
| LMArena Text: math | 1378 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: mathematical work | 1378 | Not measured | Only MiniMax M2.5 measured |
| Neither model has a result on the other 9 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | MiniMax M2.5 | Hy4 preview | Leader |
|---|---|---|---|
| MMLU Pro | 80.1% | Not measured | Only MiniMax M2.5 measured |
| LegalBench (Vals AI) | 80.0% | 83.8% | Hy4 preview |
| CaseLaw (Vals AI) | 53.5% | Not measured | Only MiniMax M2.5 measured |
| CorpFin (Vals AI) | 59.6% | Not measured | Only MiniMax M2.5 measured |
| TaxEval (Vals AI) | 68.2% | Not measured | Only MiniMax M2.5 measured |
| MedQA (Vals AI) | 92.5% | Not measured | Only MiniMax M2.5 measured |
| MedCode (Vals AI) | Not measured | 43.3% | Only Hy4 preview measured |
| LMArena Text: science | 1369 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: medicine and healthcare | 1357 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: legal and government | 1366 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: business and finance | 1356 | Not measured | Only MiniMax M2.5 measured |
| Neither model has a result on the other 7 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | MiniMax M2.5 | Hy4 preview | Leader |
|---|---|---|---|
| Design Arena: websites | 1222 | Not measured | Only MiniMax M2.5 measured |
| Design Arena: UI components | 1173 | Not measured | Only MiniMax M2.5 measured |
| Design Arena: game dev | 1176 | Not measured | Only MiniMax M2.5 measured |
| Design Arena: data viz | 1172 | Not measured | Only MiniMax M2.5 measured |
| Design Arena: 3D | 1170 | Not measured | Only MiniMax M2.5 measured |
| Design Arena: all code categories | 1207 | Not measured | Only MiniMax M2.5 measured |
| Design Arena: SVG | 1150 | Not measured | Only MiniMax M2.5 measured |
| Neither model has a result on the other 2 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index24 boards, none shared
| Benchmark | MiniMax M2.5 | Hy4 preview | Leader |
|---|---|---|---|
| Vals Index | Not measured | 53.2% | Only Hy4 preview measured |
| Public Benefits Bench (Vals AI) | Not measured | 68.6% | Only Hy4 preview measured |
| MedScribe (Vals AI) | Not measured | 83.6% | Only Hy4 preview measured |
| IFBench | 71.6% | Not measured | Only MiniMax M2.5 measured |
| Long context reasoning (AA-LCR) | 73.3% | Not measured | Only MiniMax M2.5 measured |
| CL-bench | 11.4% | Not measured | Only MiniMax M2.5 measured |
| CL-bench Life | 6.3% | Not measured | Only MiniMax M2.5 measured |
| LMArena Text | 1359 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: instruction following | 1353 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: creative writing | 1331 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: English | 1380 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: non-English | 1338 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: Chinese | 1393 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: German | 1361 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: Japanese | 1171 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: Korean | 1233 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: French | 1363 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: Spanish | 1353 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: Russian | 1359 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: Polish | 1334 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: multi-turn | 1364 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: longer queries | 1366 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: writing and language | 1345 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: entertainment and media | 1329 | Not measured | Only MiniMax M2.5 measured |
| Neither model has a result on the other 22 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | MiniMax M2.5 | Hy4 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
MiniMax M2.5 costs less
Repository review
50K input + 3K output tokens
MiniMax M2.5 costs less
Agent loop
200K input + 10K output tokens
MiniMax M2.5 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 M2.5 | Tencent Hy4 preview |
|---|---|---|
| Maker | MiniMax | Tencent |
| Weights | Open weights | Open weights |
| Released | February 12, 2026 | August 28, 2026 |
| Context window | 205K | 1.05M |
| Input $/Mtok | $0.30 | $0.834 |
| Output $/Mtok | $1.20 | $2.501 |
| Coding index | 37.2 | 44.3 |
| Independent measurements behind it | 3 | 3 |
| Cost per solved task | $0.62 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is MiniMax M2.5 better than Hy4 preview for coding?
Pick Hy4 preview for coding: it scores 44.3 on the Vibe Coding Index against 37.2 for MiniMax M2.5. Pick MiniMax M2.5 for output tokens 2.1x cheaper ($1.20 vs $2.501 per million).
Which is cheaper, MiniMax M2.5 or Hy4 preview?
MiniMax M2.5 costs $0.30 per million input tokens and $1.20 per million output tokens; Hy4 preview costs $0.834 and $2.501. Cost per solved task is known for MiniMax M2.5 only.
Which has the bigger context window, MiniMax M2.5 or Hy4 preview?
Hy4 preview, with 1.05M tokens against 205K.
How many benchmarks is the MiniMax M2.5 vs Hy4 preview comparison based on?
6 benchmarks have a result for both models as of October 22, 2026. MiniMax M2.5's coding index rests on 3 independent benchmarks and Hy4 preview's on 3. Where only one model has a result, the page says so instead of naming a winner.