Model comparison
Muse Spark 1.2 vs Muse Spark 1.3
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 50.3 on the Noometry Index.
Last verified . 26 shared benchmarks.
MetaSummary
- They share 26 benchmarks with published results for both. Muse Spark 1.2 scores higher in 1 category and Muse Spark 1.3 in 9 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Muse Spark 1.3 leads 73.1 to 46.4.
- The biggest single-benchmark swing is APEX-Agents: 36.4% for Muse Spark 1.2 and 57.8% for Muse Spark 1.3.
- Both cost about the same: $1.25 input and $4.25 output per million tokens.
Side by side
| Muse Spark 1.2 | Muse Spark 1.3 | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 50.3 | 54.8 |
| Released | 2026-08-05 | 2026-09-02 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 131K | 131K |
| Input $ / M tokens | $1.25 | $1.25 |
| Output $ / M tokens | $4.25 | $4.25 |
| Results tracked | 31 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.3 leads
Muse Spark 1.2: 49.2 (#51), Muse Spark 1.3: 56.6 (#21)
| Benchmark | Muse Spark 1.2 | Muse Spark 1.3 |
|---|---|---|
| LMArena WebDev | 1533 | 1657 |
| SciCode | 56.4% | 59.7% |
| LMArena Coding | 1495 | 1514 |
| DeepSWE | 54.9% | — |
| CursorBench | — | 41.6% |
| FrontierSWE | 12% | — |
| WeirdML | 60.3% | — |
Agentic & Tool Use Muse Spark 1.3 leads
Muse Spark 1.2: 29.4 (#87), Muse Spark 1.3: 38.6 (#30)
| Benchmark | Muse Spark 1.2 | Muse Spark 1.3 |
|---|---|---|
| APEX-Agents | 36.4% | 57.8% |
| GDP.pdf | 16% | 27.6% |
Reasoning Muse Spark 1.3 leads
Muse Spark 1.2: 51.3 (#34), Muse Spark 1.3: 54.0 (#27)
| Benchmark | Muse Spark 1.2 | Muse Spark 1.3 |
|---|---|---|
| NYT Connections (extended) | 79.2% | 85.1% |
| CritPt | 17.7% | 26% |
| LMArena Hard Prompts | 1486 | 1503 |
| DTBench | 94.7% | 96.5% |
| LMCA | 48.4% | 53.9% |
| Epoch Capabilities Index | 154.87 | 156.75 |
| SimpleBench | 74.5% | — |
| Chess Puzzles | — | 38% |
| Mystery Game Puzzles | — | 25% |
| Bench to the Future 3 | — | 0.14 |
Math Muse Spark 1.3 leads
Muse Spark 1.2: 46.4 (#70), Muse Spark 1.3: 73.1 (#21)
| Benchmark | Muse Spark 1.2 | Muse Spark 1.3 |
|---|---|---|
| ProofBench | 43% | 58% |
| LMArena Math | 1471 | 1494 |
| FrontierMath (Tiers 1-3) | — | 74.4% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 99.2% |
Knowledge Muse Spark 1.2 leads
Muse Spark 1.2: 54.1 (#53), Muse Spark 1.3: 42.6 (#95)
| Benchmark | Muse Spark 1.2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Expert | 1480 | 1516 |
| SimpleQA Verified | 60.3% | — |
Multimodal Too close to call
Muse Spark 1.2: 43.4 (#25), Muse Spark 1.3: 43.7 (#22)
| Benchmark | Muse Spark 1.2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Vision | 1305 | 1309 |
| LMArena Document | — | 1471 |
Multilingual Too close to call
Muse Spark 1.2: 57.1 (#11), Muse Spark 1.3: 57.4 (#8)
| Benchmark | Muse Spark 1.2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Non-English | 1478 | 1481 |
| LMArena Chinese | 1511 | 1529 |
| LMArena French | 1513 | 1524 |
| LMArena Russian | 1487 | 1490 |
| LMArena Spanish | 1498 | 1490 |
| LMArena German | — | 1515 |
| LMArena Japanese | — | 1474 |
| LMArena Korean | — | 1501 |
Instruction Following Too close to call
Muse Spark 1.2: 76.7 (#36), Muse Spark 1.3: 77.5 (#22)
| Benchmark | Muse Spark 1.2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Instruction Following | 1461 | 1477 |
Long Context Too close to call
Muse Spark 1.2: 45.2 (#48), Muse Spark 1.3: 45.6 (#32)
| Benchmark | Muse Spark 1.2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Longer Query | 1475 | 1488 |
Writing & Preference Muse Spark 1.3 leads
Muse Spark 1.2: 72.3 (#14), Muse Spark 1.3: 73.6 (#9)
| Benchmark | Muse Spark 1.2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Text | 1482 | 1490 |
| LMArena Creative Writing | 1449 | 1455 |
| EQ-Bench Creative Writing | 1840 | 1906 |
| LMArena Multi-Turn | 1494 | 1482 |
Frequently asked questions
Is Muse Spark 1.2 better than Muse Spark 1.3?
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 50.3 on the Noometry Index.
Which is cheaper, Muse Spark 1.2 or Muse Spark 1.3?
Muse Spark 1.3 is cheaper. It lists at $1.25 per million input tokens and $4.25 per million output tokens; Muse Spark 1.2 lists at $1.25 and $4.25.
Is Muse Spark 1.2 or Muse Spark 1.3 better for coding?
Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 49.2 in the Noometry coding category.
Which has the bigger context window?
Both accept 1.05M tokens.
How many benchmarks do Muse Spark 1.2 and Muse Spark 1.3 share?
26 benchmarks have published results for both models. Muse Spark 1.2 has 31 scored results on Noometry and Muse Spark 1.3 has 37.