Model comparison
Llama 3.2 90B vs Muse Spark
Muse Spark is the stronger model overall, scoring 50.6 to 27.5 on the Noometry Index.
Last verified . 4 shared benchmarks.
MetaSummary
- They share 4 benchmarks with published results for both. Llama 3.2 90B scores higher in 0 categories and Muse Spark in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 21.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.6% for Llama 3.2 90B and 88.9% for Muse Spark.
- Llama 3.2 90B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.2 90B | Muse Spark | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 27.5 | 50.6 |
| Released | 2024-09-24 | 2026-04-08 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.2 90B: —, Muse Spark: 46.2 (#69)
| Benchmark | Llama 3.2 90B | Muse Spark |
|---|---|---|
| SciCode | — | 51.5% |
| LMArena Coding | — | 1481 |
Agentic & Tool Use Not comparable
Llama 3.2 90B: 30.0 (#80), Muse Spark: —
| Benchmark | Llama 3.2 90B | Muse Spark |
|---|---|---|
| BALROG | 27.3% | — |
Reasoning Muse Spark leads
Llama 3.2 90B: 21.7 (#217), Muse Spark: 35.9 (#67)
| Benchmark | Llama 3.2 90B | Muse Spark |
|---|---|---|
| Epoch Capabilities Index | 125.5 | 152.04 |
| CritPt | — | 11.3% |
| EnigmaEval | 0.4% | — |
| LMArena Hard Prompts | — | 1474 |
Math Muse Spark leads
Llama 3.2 90B: 11.1 (#308), Muse Spark: 47.8 (#66)
| Benchmark | Llama 3.2 90B | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.6% | 88.9% |
| ProofBench | — | 17% |
| LMArena Math | — | 1455 |
| MATH Level 5 | 39.4% | — |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Muse Spark leads
Llama 3.2 90B: 21.7 (#274), Muse Spark: 65.7 (#13)
| Benchmark | Llama 3.2 90B | Muse Spark |
|---|---|---|
| GPQA Diamond | 41% | 89.8% |
| Humanity's Last Exam | — | 40.6% |
| LMArena Expert | — | 1457 |
| MMLU | 80.3% | — |
Multimodal Muse Spark leads
Llama 3.2 90B: 25.4 (#124), Muse Spark: 43.4 (#24)
| Benchmark | Llama 3.2 90B | Muse Spark |
|---|---|---|
| LMArena Vision | 1000 | 1306 |
| GeoBench | 52% | — |
| LMArena Document | — | 1444 |
Multilingual Not comparable
Llama 3.2 90B: —, Muse Spark: 56.1 (#24)
| Benchmark | Llama 3.2 90B | Muse Spark |
|---|---|---|
| LMArena Non-English | — | 1464 |
| LMArena Chinese | — | 1509 |
| LMArena French | — | 1497 |
| LMArena German | — | 1497 |
| LMArena Korean | — | 1459 |
| LMArena Russian | — | 1466 |
| LMArena Spanish | — | 1472 |
Instruction Following Not comparable
Llama 3.2 90B: —, Muse Spark: 75.9 (#51)
| Benchmark | Llama 3.2 90B | Muse Spark |
|---|---|---|
| LMArena Instruction Following | — | 1442 |
Long Context Not comparable
Llama 3.2 90B: —, Muse Spark: 44.4 (#69)
| Benchmark | Llama 3.2 90B | Muse Spark |
|---|---|---|
| LMArena Longer Query | — | 1451 |
Writing & Preference Not comparable
Llama 3.2 90B: —, Muse Spark: 66.0 (#39)
| Benchmark | Llama 3.2 90B | Muse Spark |
|---|---|---|
| LMArena Text | — | 1474 |
| LMArena Creative Writing | — | 1459 |
| LMArena Multi-Turn | — | 1477 |
Frequently asked questions
Is Llama 3.2 90B better than Muse Spark?
Muse Spark is the stronger model overall, scoring 50.6 to 27.5 on the Noometry Index.
How many benchmarks do Llama 3.2 90B and Muse Spark share?
4 benchmarks have published results for both models. Llama 3.2 90B has 9 scored results on Noometry and Muse Spark has 27.