Model comparison
Muse Glimmer vs Muse Spark
Muse Spark is the stronger model overall, scoring 50.6 to 41.7 on the Noometry Index.
Last verified . 14 shared benchmarks.
Summary
- They share 14 benchmarks with published results for both. Muse Glimmer scores higher in 0 categories and Muse Spark in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 38.5.
- The biggest single-benchmark swing is CritPt: 2.6% for Muse Glimmer and 11.3% for Muse Spark.
- Muse Glimmer has downloadable open weights; the other is API-only.
Side by side
| Muse Glimmer | Muse Spark | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 41.7 | 50.6 |
| Released | 2026-08-10 | 2026-04-08 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark leads
Muse Glimmer: 40.4 (#142), Muse Spark: 46.2 (#69)
| Benchmark | Muse Glimmer | Muse Spark |
|---|---|---|
| SciCode | 44.9% | 51.5% |
| LMArena Coding | 1416 | 1481 |
| LMArena WebDev | 1355 | — |
Reasoning Muse Spark leads
Muse Glimmer: 25.7 (#144), Muse Spark: 35.9 (#67)
| Benchmark | Muse Glimmer | Muse Spark |
|---|---|---|
| CritPt | 2.6% | 11.3% |
| LMArena Hard Prompts | 1396 | 1474 |
| Epoch Capabilities Index | — | 152.04 |
Math Muse Spark leads
Muse Glimmer: 38.8 (#125), Muse Spark: 47.8 (#66)
| Benchmark | Muse Glimmer | Muse Spark |
|---|---|---|
| LMArena Math | 1417 | 1455 |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 17% |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Muse Spark leads
Muse Glimmer: 38.5 (#143), Muse Spark: 65.7 (#13)
| Benchmark | Muse Glimmer | Muse Spark |
|---|---|---|
| LMArena Expert | 1386 | 1457 |
| GPQA Diamond | — | 89.8% |
| Humanity's Last Exam | — | 40.6% |
Multimodal Not comparable
Muse Glimmer: —, Muse Spark: 43.4 (#24)
| Benchmark | Muse Glimmer | Muse Spark |
|---|---|---|
| LMArena Vision | — | 1306 |
| LMArena Document | — | 1444 |
Multilingual Muse Spark leads
Muse Glimmer: 50.5 (#122), Muse Spark: 56.1 (#24)
| Benchmark | Muse Glimmer | Muse Spark |
|---|---|---|
| LMArena Non-English | 1384 | 1464 |
| LMArena Chinese | 1412 | 1509 |
| LMArena Russian | 1390 | 1466 |
| LMArena French | — | 1497 |
| LMArena German | — | 1497 |
| LMArena Korean | — | 1459 |
| LMArena Spanish | — | 1472 |
Instruction Following Muse Spark leads
Muse Glimmer: 72.6 (#135), Muse Spark: 75.9 (#51)
| Benchmark | Muse Glimmer | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1375 | 1442 |
Long Context Muse Spark leads
Muse Glimmer: 42.1 (#129), Muse Spark: 44.4 (#69)
| Benchmark | Muse Glimmer | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1382 | 1451 |
Writing & Preference Muse Spark leads
Muse Glimmer: 57.5 (#126), Muse Spark: 66.0 (#39)
| Benchmark | Muse Glimmer | Muse Spark |
|---|---|---|
| LMArena Text | 1389 | 1474 |
| LMArena Creative Writing | 1339 | 1459 |
| LMArena Multi-Turn | 1399 | 1477 |
Frequently asked questions
Is Muse Glimmer better than Muse Spark?
Muse Spark is the stronger model overall, scoring 50.6 to 41.7 on the Noometry Index.
Is Muse Glimmer or Muse Spark better for coding?
Muse Spark scores higher on coding benchmarks: 46.2 versus 40.4 in the Noometry coding category.
How many benchmarks do Muse Glimmer and Muse Spark share?
14 benchmarks have published results for both models. Muse Glimmer has 15 scored results on Noometry and Muse Spark has 27.