Model comparison
Mistral Large 4 vs Muse Spark 1.3
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 43.1 on the Noometry Index. Mistral Large 4 costs 1.9× less per token, which makes it the better buy when Muse Spark 1.3's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
Mistral AI
MetaSummary
- They share 14 benchmarks with published results for both. Mistral Large 4 scores higher in 0 categories and Muse Spark 1.3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Muse Spark 1.3 leads 73.1 to 40.4.
- The biggest single-benchmark swing is NYT Connections (extended): 27.4% for Mistral Large 4 and 85.1% for Muse Spark 1.3.
- Mistral Large 4 is cheaper at $0.68 / $2.09 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.3.
Side by side
| Mistral Large 4 | Muse Spark 1.3 | |
|---|---|---|
| Provider | Mistral AI | Meta |
| Noometry Index | 43.1 | 54.8 |
| Released | 2026-10-06 | 2026-09-02 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 262K | 131K |
| Input $ / M tokens | $0.68 | $1.25 |
| Output $ / M tokens | $2.09 | $4.25 |
| Results tracked | 15 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.3 leads
Mistral Large 4: 48.6 (#57), Muse Spark 1.3: 56.6 (#21)
| Benchmark | Mistral Large 4 | Muse Spark 1.3 |
|---|---|---|
| LMArena WebDev | 1541 | 1657 |
| LMArena Coding | 1475 | 1514 |
| CursorBench | — | 41.6% |
| SciCode | — | 59.7% |
Agentic & Tool Use Not comparable
Mistral Large 4: —, Muse Spark 1.3: 38.6 (#30)
| Benchmark | Mistral Large 4 | Muse Spark 1.3 |
|---|---|---|
| APEX-Agents | — | 57.8% |
| GDP.pdf | — | 27.6% |
Reasoning Muse Spark 1.3 leads
Mistral Large 4: 22.5 (#192), Muse Spark 1.3: 54.0 (#27)
| Benchmark | Mistral Large 4 | Muse Spark 1.3 |
|---|---|---|
| NYT Connections (extended) | 27.4% | 85.1% |
| LMArena Hard Prompts | 1444 | 1503 |
| CritPt | — | 26% |
| Chess Puzzles | — | 38% |
| Mystery Game Puzzles | — | 25% |
| DTBench | — | 96.5% |
| LMCA | — | 53.9% |
| Bench to the Future 3 | — | 0.14 |
| Epoch Capabilities Index | — | 156.75 |
Math Muse Spark 1.3 leads
Mistral Large 4: 40.4 (#91), Muse Spark 1.3: 73.1 (#21)
| Benchmark | Mistral Large 4 | Muse Spark 1.3 |
|---|---|---|
| LMArena Math | 1488 | 1494 |
| FrontierMath (Tiers 1-3) | — | 74.4% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 99.2% |
| ProofBench | — | 58% |
Knowledge Muse Spark 1.3 leads
Mistral Large 4: 36.6 (#166), Muse Spark 1.3: 42.6 (#95)
| Benchmark | Mistral Large 4 | Muse Spark 1.3 |
|---|---|---|
| LMArena Expert | 1447 | 1516 |
| SimpleQA Verified | 20% | — |
Multimodal Not comparable
Mistral Large 4: —, Muse Spark 1.3: 43.7 (#22)
| Benchmark | Mistral Large 4 | Muse Spark 1.3 |
|---|---|---|
| LMArena Vision | — | 1309 |
| LMArena Document | — | 1471 |
Multilingual Muse Spark 1.3 leads
Mistral Large 4: 52.6 (#82), Muse Spark 1.3: 57.4 (#8)
| Benchmark | Mistral Large 4 | Muse Spark 1.3 |
|---|---|---|
| LMArena Non-English | 1415 | 1481 |
| LMArena Chinese | 1491 | 1529 |
| LMArena Russian | 1414 | 1490 |
| LMArena French | — | 1524 |
| LMArena German | — | 1515 |
| LMArena Japanese | — | 1474 |
| LMArena Korean | — | 1501 |
| LMArena Spanish | — | 1490 |
Instruction Following Muse Spark 1.3 leads
Mistral Large 4: 75.0 (#76), Muse Spark 1.3: 77.5 (#22)
| Benchmark | Mistral Large 4 | Muse Spark 1.3 |
|---|---|---|
| LMArena Instruction Following | 1424 | 1477 |
Long Context Muse Spark 1.3 leads
Mistral Large 4: 43.6 (#89), Muse Spark 1.3: 45.6 (#32)
| Benchmark | Mistral Large 4 | Muse Spark 1.3 |
|---|---|---|
| LMArena Longer Query | 1429 | 1488 |
Writing & Preference Muse Spark 1.3 leads
Mistral Large 4: 60.4 (#97), Muse Spark 1.3: 73.6 (#9)
| Benchmark | Mistral Large 4 | Muse Spark 1.3 |
|---|---|---|
| LMArena Text | 1427 | 1490 |
| LMArena Creative Writing | 1361 | 1455 |
| LMArena Multi-Turn | 1424 | 1482 |
| EQ-Bench Creative Writing | — | 1906 |
Frequently asked questions
Is Mistral Large 4 better than Muse Spark 1.3?
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 43.1 on the Noometry Index. Mistral Large 4 costs 1.9× less per token, which makes it the better buy when Muse Spark 1.3's lead doesn't matter for your workload.
Which is cheaper, Mistral Large 4 or Muse Spark 1.3?
Mistral Large 4 is cheaper. It lists at $0.68 per million input tokens and $2.09 per million output tokens; Muse Spark 1.3 lists at $1.25 and $4.25.
Is Mistral Large 4 or Muse Spark 1.3 better for coding?
Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 48.6 in the Noometry coding category.
Which has the bigger context window?
Both accept 1.05M tokens.
How many benchmarks do Mistral Large 4 and Muse Spark 1.3 share?
14 benchmarks have published results for both models. Mistral Large 4 has 15 scored results on Noometry and Muse Spark 1.3 has 37.