MiniMax M3.1 Flash vs Hy4 preview
MiniMax M3.1 Flash leads Hy4 preview on coding, 59.0 to 44.3 on the Vibe Coding Index, and MiniMax M3.1 Flash costs 4.2x less per output token ($0.60 vs $2.501 per million). Updated October 22, 2026; 9 benchmarks have a result for both.
MiniMax M3.1 Flash or Hy4 preview: which to pick
Pick MiniMax M3.1 Flash for coding: it scores 59.0 on the Vibe Coding Index against 44.3 for Hy4 preview.
Pick Hy4 preview for a larger context window (1.05M against 1M tokens) and work measured by LMArena WebDev or Vibe Code Bench (Vals AI), where it leads.
- Shared results
- 9
- MiniMax M3.1 Flash only
- 11
- Hy4 preview only
- 15
- 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
MiniMax M3.1 Flash
MiniMax M3.1 Flash scores 59.0 against 44.3.
4 and 3 benchmarks behind the scores
Intelligence
AA Intelligence Index
No call
Only MiniMax M3.1 Flash has a AA Intelligence Index result, 42.7.
Directional only
General
Vals Index
MiniMax M3.1 Flash
MiniMax M3.1 Flash leads, 53.8% against 53.2%.
Same board, both measured
Long documents
Listed context window
Hy4 preview
Hy4 preview takes 1.05M tokens against 1M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiniMax M3.1 Flash
MiniMax M3.1 Flash $0.0004, Hy4 preview $0.0021 per turn.
List prices
At a glance
- Coding index
- MiniMax M3.1 Flash 59.0 from 4 benchmarks, Hy4 preview 44.3 from 3 benchmarks.
- Widest category
- Coding, 8.9 points apart on average over 5 shared benchmarks.
- Widest single gap
- Terminal-Bench 4 (Vals AI): MiniMax M3.1 Flash 25.3% against Hy4 preview 8.1%, 22.9 points apart on a 0 to 100 scale.
- Output price
- MiniMax M3.1 Flash $0.60 against Hy4 preview $2.501 per million output tokens, 4.2x apart.
- Context window
- MiniMax M3.1 Flash takes 1M 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 M3.1 Flash | Bars | Hy4 preview | Ties |
|---|---|---|---|---|
| Coding | 1 | 4 | ||
| Agentic work | 0 | 3 | ||
| General | 1 | 0 | ||
| All shared boards | 2 | 7 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index14
| Benchmark | MiniMax M3.1 Flash | Hy4 preview | Leader |
|---|---|---|---|
| LiveBench coding | 83.9% | Not measured | Only MiniMax M3.1 Flash measured |
| LMArena WebDev | 1587 | 1631 | Hy4 preview |
| Terminal-Bench 4 (Vals AI) | 25.3% | 8.1% | MiniMax M3.1 Flash |
| Vibe Code Bench (Vals AI) | 73.9% | 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 |
| SciCode | 53.4% | Not measured | Only MiniMax M3.1 Flash measured |
| LMArena WebDev: React | 1609 | 1653 | Hy4 preview |
| LMArena WebDev: HTML | 1529 | 1620 | Hy4 preview |
| Neither model has a result on the other 31 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | MiniMax M3.1 Flash | Hy4 preview | Leader |
|---|---|---|---|
| AA Intelligence Index | 42.7 | Not measured | Only MiniMax M3.1 Flash measured |
| Neither model has a result on the other 1 board here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | MiniMax M3.1 Flash | Hy4 preview | Leader |
|---|---|---|---|
| LiveBench research | 72.7% | Not measured | Only MiniMax M3.1 Flash measured |
| LiveBench browser | 92.0% | Not measured | Only MiniMax M3.1 Flash measured |
| LiveBench long agentic | 34.7% | Not measured | Only MiniMax M3.1 Flash measured |
| 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) | 32.1% | 32.6% | Hy4 preview |
| Legal Research Bench (Vals AI) | 34.1% | 45.2% | Hy4 preview |
| Harvey's Legal Agent Benchmark (Vals AI) | 7.5% | 8.8% | Hy4 preview |
| 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 |
| Neither model has a result on the other 31 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | MiniMax M3.1 Flash | Hy4 preview | Leader |
|---|---|---|---|
| LiveBench reasoning | 82.9% | Not measured | Only MiniMax M3.1 Flash measured |
| Humanity's Last Exam (Artificial Analysis run) | 48.0% | Not measured | Only MiniMax M3.1 Flash measured |
| Neither model has a result on the other 21 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | MiniMax M3.1 Flash | Hy4 preview | Leader |
|---|---|---|---|
| ProofBench | Not measured | 75.0% | Only Hy4 preview measured |
| Neither model has a result on the other 13 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | MiniMax M3.1 Flash | Hy4 preview | Leader |
|---|---|---|---|
| LegalBench (Vals AI) | Not measured | 83.8% | Only Hy4 preview measured |
| MedCode (Vals AI) | Not measured | 43.3% | Only Hy4 preview measured |
| Neither model has a result on the other 18 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | MiniMax M3.1 Flash | Hy4 preview | Leader |
|---|---|---|---|
| LiveBench design | 74.0% | Not measured | Only MiniMax M3.1 Flash measured |
| Neither model has a result on the other 8 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | MiniMax M3.1 Flash | Hy4 preview | Leader |
|---|---|---|---|
| Vals Index | 53.8% | 53.2% | MiniMax M3.1 Flash |
| LiveBench data analysis | 71.4% | Not measured | Only MiniMax M3.1 Flash 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 |
| Long context reasoning (AA-LCR) | 79.7% | Not measured | Only MiniMax M3.1 Flash measured |
| Neither model has a result on the other 43 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | MiniMax M3.1 Flash | 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 M3.1 Flash costs less
Repository review
50K input + 3K output tokens
MiniMax M3.1 Flash costs less
Agent loop
200K input + 10K output tokens
MiniMax M3.1 Flash 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 M3.1 Flash | Tencent Hy4 preview |
|---|---|---|
| Maker | MiniMax | Tencent |
| Weights | No public weights listed | Open weights |
| Released | October 19, 2026 | August 28, 2026 |
| Context window | 1M | 1.05M |
| Input $/Mtok | $0.15 | $0.834 |
| Output $/Mtok | $0.60 | $2.501 |
| Coding index | 59.0 | 44.3 |
| Independent measurements behind it | 4 | 3 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is MiniMax M3.1 Flash better than Hy4 preview for coding?
Pick MiniMax M3.1 Flash for coding: it scores 59.0 on the Vibe Coding Index against 44.3 for Hy4 preview. Pick Hy4 preview for a larger context window (1.05M against 1M tokens) and work measured by LMArena WebDev or Vibe Code Bench (Vals AI), where it leads.
Which is cheaper, MiniMax M3.1 Flash or Hy4 preview?
MiniMax M3.1 Flash costs $0.15 per million input tokens and $0.60 per million output tokens; Hy4 preview costs $0.834 and $2.501. Cost per solved task is known for neither of them.
Which has the bigger context window, MiniMax M3.1 Flash or Hy4 preview?
Hy4 preview, with 1.05M tokens against 1M.
How many benchmarks is the MiniMax M3.1 Flash vs Hy4 preview comparison based on?
9 benchmarks have a result for both models as of October 22, 2026. MiniMax M3.1 Flash's coding index rests on 4 independent benchmarks and Hy4 preview's on 3. Where only one model has a result, the page says so instead of naming a winner.