Mistral Large 4 vs Hy4 preview
Updated October 21, 2026. 16 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick Hy4 preview for coding: it scores 61.6 on the Vibe Coding Index against 55.3 for Mistral Large 4, though on 1 benchmark against 2.
Pick Mistral Large 4 when what matters is Terminal-Bench 4 (Vals AI) or Vibe Code Bench (Vals AI), where it leads.
- Shared results
- 16
- Mistral Large 4 only
- 65
- Hy4 preview only
- 8
- Like-for-like categories
- 5 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.
Coding
Vibe Coding Index, four public coding benchmarks
Hy4 preview
Hy4 preview scores 61.6 against 55.3.
2 and 1 benchmarks behind the scores
Intelligence
AA Intelligence Index
No call
Only Mistral Large 4 has a AA Intelligence Index result, 38.4.
Directional only
Web design
Design Arena: websites
No call
Only Mistral Large 4 has a Design Arena: websites result, 1258.
Directional only
General
Vals Index
No call
Only Hy4 preview has a Vals Index result, 53.2%.
Directional only
Long documents
Listed context window
No call
Both take 1.05M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Hy4 preview
Mistral Large 4 $0.0034, Hy4 preview $0.0021 per turn.
List prices
At a glance
- Coding index
- Mistral Large 4 55.3 from 2 benchmarks, Hy4 preview 61.6 from 1 benchmark.
- Widest category
- Math, 65.0 points apart on average over 1 shared benchmark.
- Widest single gap
- ProofBench: Mistral Large 4 10.0% against Hy4 preview 75.0%, 65.0 points apart on a 0 to 100 scale.
- Output price
- Mistral Large 4 $4.18 against Hy4 preview $2.501 per million output tokens, 1.7x apart.
- Context window
- Both take 1.05M tokens.
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 | Mistral Large 4 | Bars | Hy4 preview | Ties |
|---|---|---|---|---|
| Coding | 2 | 5 | ||
| Agentic work | 1 | 5 | ||
| Math | 0 | 1 | ||
| Knowledge | 0 | 1 | ||
| General | 0 | 1 | ||
| All shared boards | 3 | 13 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index25
| Benchmark | Mistral Large 4 | Hy4 preview | Leader |
|---|---|---|---|
| LiveBench coding | 60.0% | Not measured | Only Mistral Large 4 measured |
| LMArena WebDev | 1543 | 1631 | Hy4 preview |
| Terminal-Bench 4 (Vals AI) | 27.8% | 8.1% | Mistral Large 4 |
| Vibe Code Bench (Vals AI) | 78.4% | 77.5% | Mistral Large 4 |
| Code migration (Vals AI) | 30.6% | 47.4% | Hy4 preview |
| ProgramBench (Vals AI) | Not measured | 0.0% | Only Hy4 preview measured |
| IOI (Vals AI) | 45.3% | 59.3% | Hy4 preview |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 55.1% | Only Hy4 preview measured |
| SWE-bench Multimodal (Vals AI) | 33.1% | Not measured | Only Mistral Large 4 measured |
| Vibe Code Bench 1-100 (Vals AI) | 14.3% | Not measured | Only Mistral Large 4 measured |
| CyberBench (Vals AI) | Not measured | 65.4% | Only Hy4 preview measured |
| SciCode | 54.2% | Not measured | Only Mistral Large 4 measured |
| FrontierCode | 39.4% | Not measured | Only Mistral Large 4 measured |
| ALE-Bench | 1213.2 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: coding | 1478 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: software and IT | 1467 | Not measured | Only Mistral Large 4 measured |
| LMArena WebDev: React | 1559 | 1653 | Hy4 preview |
| LMArena WebDev: HTML | 1487 | 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 | Mistral Large 4 | Hy4 preview | Leader |
|---|---|---|---|
| AA Intelligence Index | 38.4 | Not measured | Only Mistral Large 4 measured |
| Epoch Capabilities Index | 150.0 | Not measured | Only Mistral Large 4 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index15
| Benchmark | Mistral Large 4 | Hy4 preview | Leader |
|---|---|---|---|
| LiveBench research | 28.1% | Not measured | Only Mistral Large 4 measured |
| LiveBench browser | 8.0% | Not measured | Only Mistral Large 4 measured |
| LiveBench long agentic | 11.8% | Not measured | Only Mistral Large 4 measured |
| SREBench (Vals AI) | Not measured | 2.3% | Only Hy4 preview measured |
| Finance Agent (Vals AI) | 54.7% | 55.1% | Hy4 preview |
| Tax Agent Bench (Vals AI) | 30.4% | 32.6% | Hy4 preview |
| Legal Research Bench (Vals AI) | 31.7% | 45.2% | Hy4 preview |
| Harvey's Legal Agent Benchmark (Vals AI) | 17.5% | 8.8% | Mistral Large 4 |
| Excel Modeling Benchmark (Vals AI) | 56.2% | 58.1% | Hy4 preview |
| BioMysteryBench (Vals AI) | 67.0% | 69.3% | Hy4 preview |
| Terminal-Bench-Science (Vals AI) | Not measured | 1.4% | Only Hy4 preview measured |
| Neither model has a result on the other 28 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index10 boards, none shared
| Benchmark | Mistral Large 4 | Hy4 preview | Leader |
|---|---|---|---|
| LiveBench reasoning | 83.9% | Not measured | Only Mistral Large 4 measured |
| MysteryMechanism (Vals AI) | 12.2% | Not measured | Only Mistral Large 4 measured |
| Humanity's Last Exam (Artificial Analysis run) | 35.0% | Not measured | Only Mistral Large 4 measured |
| GPQA Diamond (Epoch AI run) | 88.1% | Not measured | Only Mistral Large 4 measured |
| Chess puzzles | 33.0% | Not measured | Only Mistral Large 4 measured |
| Mystery game puzzles | 17.0% | Not measured | Only Mistral Large 4 measured |
| LMArena Text: hard prompts | 1444 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: expert | 1444 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: hard prompts in English | 1442 | Not measured | Only Mistral Large 4 measured |
| LMArena Vision: diagrams | 1288 | Not measured | Only Mistral Large 4 measured |
| Neither model has a result on the other 11 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Mistral Large 4 | Hy4 preview | Leader |
|---|---|---|---|
| OTIS Mock AIME | 98.3% | Not measured | Only Mistral Large 4 measured |
| FrontierMath, tiers 1 to 3 | 58.6% | Not measured | Only Mistral Large 4 measured |
| FrontierMath, tier 4 | 26.8% | Not measured | Only Mistral Large 4 measured |
| ProofBench | 10.0% | 75.0% | Hy4 preview |
| LMArena Text: math | 1469 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: mathematical work | 1462 | Not measured | Only Mistral Large 4 measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Mistral Large 4 | Hy4 preview | Leader |
|---|---|---|---|
| LegalBench (Vals AI) | Not measured | 83.8% | Only Hy4 preview measured |
| MedCode (Vals AI) | 40.7% | 43.3% | Hy4 preview |
| SimpleQA Verified | 20.0% | Not measured | Only Mistral Large 4 measured |
| LMArena Text: science | 1448 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: medicine and healthcare | 1433 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: legal and government | 1425 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: business and finance | 1439 | Not measured | Only Mistral Large 4 measured |
| Neither model has a result on the other 10 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | Mistral Large 4 | Hy4 preview | Leader |
|---|---|---|---|
| Design Arena: websites | 1258 | Not measured | Only Mistral Large 4 measured |
| Design Arena: UI components | 1275 | Not measured | Only Mistral Large 4 measured |
| Design Arena: game dev | 1226 | Not measured | Only Mistral Large 4 measured |
| Design Arena: data viz | 1274 | Not measured | Only Mistral Large 4 measured |
| Design Arena: 3D | 1253 | Not measured | Only Mistral Large 4 measured |
| Design Arena: all code categories | 1259 | Not measured | Only Mistral Large 4 measured |
| Design Arena: SVG | 1232 | Not measured | Only Mistral Large 4 measured |
| Design Arena: ASCII art | 1203 | Not measured | Only Mistral Large 4 measured |
| LiveBench design | 65.6% | Not measured | Only Mistral Large 4 measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Mistral Large 4 | Hy4 preview | Leader |
|---|---|---|---|
| Vals Index | Not measured | 53.2% | Only Hy4 preview measured |
| LiveBench data analysis | 76.5% | Not measured | Only Mistral Large 4 measured |
| Public Benefits Bench (Vals AI) | Not measured | 68.6% | Only Hy4 preview measured |
| MedScribe (Vals AI) | 80.4% | 83.6% | Hy4 preview |
| Long context reasoning (AA-LCR) | 81.3% | Not measured | Only Mistral Large 4 measured |
| DTBench | 88.2% | Not measured | Only Mistral Large 4 measured |
| LMCA | 35.8% | Not measured | Only Mistral Large 4 measured |
| Surface Evolver Bench | 28.1% | Not measured | Only Mistral Large 4 measured |
| Furniture assembly | 20.8% | Not measured | Only Mistral Large 4 measured |
| LMArena Text | 1431 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: instruction following | 1422 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: creative writing | 1363 | Not measured | Only Mistral Large 4 measured |
| LMArena Vision | 1272 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: English | 1433 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: non-English | 1422 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: Chinese | 1492 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: Japanese | 1415 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: French | 1492 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: Spanish | 1455 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: Russian | 1417 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: multi-turn | 1435 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: longer queries | 1428 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: writing and language | 1386 | Not measured | Only Mistral Large 4 measured |
| LMArena Text: entertainment and media | 1378 | Not measured | Only Mistral Large 4 measured |
| LMArena Vision: English | 1283 | Not measured | Only Mistral Large 4 measured |
| LMArena Vision: reading text | 1284 | Not measured | Only Mistral Large 4 measured |
| Neither model has a result on the other 20 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Mistral Large 4 | 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
Hy4 preview costs less
Repository review
50K input + 3K output tokens
Hy4 preview costs less
Agent loop
200K input + 10K output tokens
Hy4 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 | Mistral Large 4 | Tencent Hy4 preview |
|---|---|---|
| Maker | Mistral AI | Tencent |
| Weights | No public weights listed | Open weights |
| Released | October 6, 2026 | August 28, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $1.36 | $0.834 |
| Output $/Mtok | $4.18 | $2.501 |
| Coding index | 55.3 | 61.6 |
| Independent measurements behind it | 2 | 1 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Mistral Large 4 better than Hy4 preview for coding?
Pick Hy4 preview for coding: it scores 61.6 on the Vibe Coding Index against 55.3 for Mistral Large 4, though on 1 benchmark against 2. Pick Mistral Large 4 when what matters is Terminal-Bench 4 (Vals AI) or Vibe Code Bench (Vals AI), where it leads.
Which is cheaper, Mistral Large 4 or Hy4 preview?
Mistral Large 4 costs $1.36 per million input tokens and $4.18 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, Mistral Large 4 or Hy4 preview?
Neither: both take 1.05M tokens.
How many benchmarks is the Mistral Large 4 vs Hy4 preview comparison based on?
16 benchmarks have a result for both models as of October 21, 2026. Mistral Large 4's coding index rests on 2 independent benchmarks and Hy4 preview's on 1. Where only one model has a result, the page says so instead of naming a winner.