Muse Spark 1.3 vs Mistral Small 4
Muse Spark 1.3 leads Mistral Small 4 on the Artificial Analysis Intelligence Index, 48.1 to 11.3, and Mistral Small 4 costs 7.1x less per output token ($0.60 vs $4.25 per million). Updated October 22, 2026; 11 benchmarks have a result for both.
Muse Spark 1.3 or Mistral Small 4: which to pick
Only Muse Spark 1.3 has a coding score, 57.4 on the Vibe Coding Index; Mistral Small 4 has none, so the two cannot be ranked on coding.
Pick Mistral Small 4 for output tokens 7.1x cheaper ($0.60 vs $4.25 per million).
- Shared results
- 11
- Muse Spark 1.3 only
- 81
- Mistral Small 4 only
- 4
- 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
Only Muse Spark 1.3 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
Muse Spark 1.3
Muse Spark 1.3 leads, 48.1 against 11.3.
Same board, both measured
Agentic work
AA Agentic Index
Muse Spark 1.3
Muse Spark 1.3 leads, 55.5 against 0.8.
Same board, both measured
Web design
Design Arena: websites
No call
Only Muse Spark 1.3 has a Design Arena: websites result, 1356.
Directional only
Long documents
Listed context window
Muse Spark 1.3
Muse Spark 1.3 takes 1.05M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Mistral Small 4
Muse Spark 1.3 $0.0034, Mistral Small 4 $0.0004 per turn.
List prices
At a glance
- Coding index
- Muse Spark 1.3 57.4 from 4 benchmarks, Mistral Small 4 not benchmarked.
- Widest category
- Agentic work, 54.7 points apart on average over 1 shared benchmark.
- Widest single gap
- Vibe Code Bench (Vals AI): Muse Spark 1.3 82.9% against Mistral Small 4 0.0%, 82.9 points apart on a 0 to 100 scale.
- Output price
- Muse Spark 1.3 $4.25 against Mistral Small 4 $0.60 per million output tokens, 7.1x apart.
- Context window
- Muse Spark 1.3 takes 1.05M tokens, Mistral Small 4 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 | Muse Spark 1.3 | Bars | Mistral Small 4 | Ties |
|---|---|---|---|---|
| Coding | 4 | 0 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 2 | 0 | ||
| General | 3 | 0 | ||
| All shared boards | 11 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index40
| Benchmark | Muse Spark 1.3 | Mistral Small 4 | Leader |
|---|---|---|---|
| LiveBench coding | 90.2% | Not measured | Only Muse Spark 1.3 measured |
| LMArena WebDev | 1659 | Not measured | Only Muse Spark 1.3 measured |
| AA Coding Index | 75.8 | 26.6 | Muse Spark 1.3 |
| Terminal-Bench 4 (Vals AI) | 10.6% | Not measured | Only Muse Spark 1.3 measured |
| Vibe Code Bench (Vals AI) | 82.9% | 0.0% | Muse Spark 1.3 |
| Code migration (Vals AI) | 27.6% | Not measured | Only Muse Spark 1.3 measured |
| ProgramBench (Vals AI) | 0.5% | Not measured | Only Muse Spark 1.3 measured |
| IOI (Vals AI) | 43.9% | Not measured | Only Muse Spark 1.3 measured |
| Terminal-Bench 2.1 (Vals AI) | 72.3% | Not measured | Only Muse Spark 1.3 measured |
| CyberBench (Vals AI) | 69.4% | Not measured | Only Muse Spark 1.3 measured |
| SciCode | 59.7% | 38.8% | Muse Spark 1.3 |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 17.4% | Only Mistral Small 4 measured |
| FrontierSWE | 25.8% | Not measured | Only Muse Spark 1.3 measured |
| ALE-Bench | 1688.3 | 497.6 | Muse Spark 1.3 |
| LMArena Text: coding | 1510 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Text: software and IT | 1511 | Not measured | Only Muse Spark 1.3 measured |
| LMArena WebDev: React | 1672 | Not measured | Only Muse Spark 1.3 measured |
| LMArena WebDev: HTML | 1653 | Not measured | Only Muse Spark 1.3 measured |
| LMArena WebDev: from an image | 1640 | Not measured | Only Muse Spark 1.3 measured |
| Neither model has a result on the other 20 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Muse Spark 1.3 | Mistral Small 4 | Leader |
|---|---|---|---|
| AA Intelligence Index | 48.1 | 11.3 | Muse Spark 1.3 |
| Epoch Capabilities Index | 157.2 | Not measured | Only Muse Spark 1.3 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Muse Spark 1.3 | Mistral Small 4 | Leader |
|---|---|---|---|
| AA Agentic Index | 55.5 | 0.8 | Muse Spark 1.3 |
| Design Arena: agents building web apps | 1297 | Not measured | Only Muse Spark 1.3 measured |
| Design Arena: agents building full-stack apps | 1295 | Not measured | Only Muse Spark 1.3 measured |
| Design Arena: agents building mobile apps | 1218 | Not measured | Only Muse Spark 1.3 measured |
| Design Arena: agents building Godot games | 1241 | Not measured | Only Muse Spark 1.3 measured |
| Design Arena: PowerPoint slides | 1219 | Not measured | Only Muse Spark 1.3 measured |
| Design Arena: spreadsheets | 1062 | Not measured | Only Muse Spark 1.3 measured |
| LiveBench research | 68.6% | Not measured | Only Muse Spark 1.3 measured |
| LiveBench browser | 80.0% | Not measured | Only Muse Spark 1.3 measured |
| LiveBench long agentic | 40.4% | Not measured | Only Muse Spark 1.3 measured |
| Finance Agent (Vals AI) | 58.9% | Not measured | Only Muse Spark 1.3 measured |
| Tax Agent Bench (Vals AI) | 36.0% | Not measured | Only Muse Spark 1.3 measured |
| Legal Research Bench (Vals AI) | 40.9% | Not measured | Only Muse Spark 1.3 measured |
| Excel Modeling Benchmark (Vals AI) | 62.7% | Not measured | Only Muse Spark 1.3 measured |
| Terminal-Bench-Science (Vals AI) | 4.3% | Not measured | Only Muse Spark 1.3 measured |
| τ²-Bench Telecom | Not measured | 41.2% | Only Mistral Small 4 measured |
| APEX-Agents | 58.6% | Not measured | Only Muse Spark 1.3 measured |
| Neither model has a result on the other 24 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Muse Spark 1.3 | Mistral Small 4 | Leader |
|---|---|---|---|
| LiveBench reasoning | 89.7% | Not measured | Only Muse Spark 1.3 measured |
| GPQA Diamond (Artificial Analysis run) | 94.1% | 76.9% | Muse Spark 1.3 |
| Humanity's Last Exam (Artificial Analysis run) | 48.7% | 9.9% | Muse Spark 1.3 |
| Chess puzzles | 37.0% | Not measured | Only Muse Spark 1.3 measured |
| Mystery game puzzles | 25.0% | Not measured | Only Muse Spark 1.3 measured |
| LMArena Text: hard prompts | 1503 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Text: expert | 1519 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Text: hard prompts in English | 1500 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Vision: diagrams | 1330 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Vision: homework | 1296 | Not measured | Only Muse Spark 1.3 measured |
| Kagi LLM Benchmark | Not measured | 40.5% | Only Mistral Small 4 measured |
| Neither model has a result on the other 11 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Muse Spark 1.3 | Mistral Small 4 | Leader |
|---|---|---|---|
| OTIS Mock AIME | 99.2% | Not measured | Only Muse Spark 1.3 measured |
| FrontierMath, tiers 1 to 3 | 74.4% | Not measured | Only Muse Spark 1.3 measured |
| FrontierMath, tier 4 | 46.3% | Not measured | Only Muse Spark 1.3 measured |
| ProofBench | 58.0% | Not measured | Only Muse Spark 1.3 measured |
| LMArena Text: math | 1497 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Text: mathematical work | 1491 | Not measured | Only Muse Spark 1.3 measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | Muse Spark 1.3 | Mistral Small 4 | Leader |
|---|---|---|---|
| LMArena Text: science | 1507 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Text: medicine and healthcare | 1493 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Text: legal and government | 1499 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Text: business and finance | 1490 | Not measured | Only Muse Spark 1.3 measured |
| Neither model has a result on the other 14 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | Muse Spark 1.3 | Mistral Small 4 | Leader |
|---|---|---|---|
| Design Arena: websites | 1356 | Not measured | Only Muse Spark 1.3 measured |
| Design Arena: UI components | 1349 | Not measured | Only Muse Spark 1.3 measured |
| Design Arena: game dev | 1328 | Not measured | Only Muse Spark 1.3 measured |
| Design Arena: data viz | 1343 | Not measured | Only Muse Spark 1.3 measured |
| Design Arena: 3D | 1358 | Not measured | Only Muse Spark 1.3 measured |
| Design Arena: all code categories | 1352 | Not measured | Only Muse Spark 1.3 measured |
| Design Arena: SVG | 1301 | Not measured | Only Muse Spark 1.3 measured |
| Design Arena: ASCII art | 1278 | Not measured | Only Muse Spark 1.3 measured |
| LiveBench design | 74.8% | Not measured | Only Muse Spark 1.3 measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | Muse Spark 1.3 | Mistral Small 4 | Leader |
|---|---|---|---|
| LiveBench data analysis | 79.6% | Not measured | Only Muse Spark 1.3 measured |
| IFBench | Not measured | 48.2% | Only Mistral Small 4 measured |
| Long context reasoning (AA-LCR) | 83.0% | 49.7% | Muse Spark 1.3 |
| DTBench | 96.5% | 70.9% | Muse Spark 1.3 |
| LMCA | 53.9% | 20.6% | Muse Spark 1.3 |
| LMArena Text | 1490 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Text: instruction following | 1479 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Text: creative writing | 1462 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Vision | 1308 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Text: English | 1495 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Text: non-English | 1481 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Text: Chinese | 1532 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Text: German | 1513 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Text: Japanese | 1470 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Text: Korean | 1490 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Text: French | 1511 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Text: Spanish | 1496 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Text: Russian | 1491 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Text: Polish | 1490 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Text: multi-turn | 1487 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Text: longer queries | 1488 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Text: writing and language | 1470 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Text: entertainment and media | 1457 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Vision: English | 1298 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Vision: Chinese | 1384 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Vision: reading text | 1319 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Vision: humor | 1293 | Not measured | Only Muse Spark 1.3 measured |
| LMArena Vision: creative writing | 1296 | Not measured | Only Muse Spark 1.3 measured |
| Neither model has a result on the other 18 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Muse Spark 1.3 | Mistral Small 4 | 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
Mistral Small 4 costs less
Repository review
50K input + 3K output tokens
Mistral Small 4 costs less
Agent loop
200K input + 10K output tokens
Mistral Small 4 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 | Meta Muse Spark 1.3 | Mistral Small 4 |
|---|---|---|
| Maker | Meta | Mistral AI |
| Weights | No public weights listed | Open weights |
| Released | September 2, 2026 | March 16, 2026 |
| Context window | 1.05M | 262K |
| Input $/Mtok | $1.25 | $0.15 |
| Output $/Mtok | $4.25 | $0.60 |
| Coding index | 57.4 | Not benchmarked |
| Independent measurements behind it | 4 | 1 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Muse Spark 1.3 better than Mistral Small 4 for coding?
Only Muse Spark 1.3 has a coding score, 57.4 on the Vibe Coding Index; Mistral Small 4 has none, so the two cannot be ranked on coding. Pick Mistral Small 4 for output tokens 7.1x cheaper ($0.60 vs $4.25 per million).
Which is cheaper, Muse Spark 1.3 or Mistral Small 4?
Muse Spark 1.3 costs $1.25 per million input tokens and $4.25 per million output tokens; Mistral Small 4 costs $0.15 and $0.60. Cost per solved task is known for neither of them.
Which has the bigger context window, Muse Spark 1.3 or Mistral Small 4?
Muse Spark 1.3, with 1.05M tokens against 262K.
How many benchmarks is the Muse Spark 1.3 vs Mistral Small 4 comparison based on?
11 benchmarks have a result for both models as of October 22, 2026. Muse Spark 1.3's coding index rests on 4 independent benchmarks and Mistral Small 4's on 1. Where only one model has a result, the page says so instead of naming a winner.