Model comparison
Muse Spark 1.2 vs Phi-3.5-mini
Muse Spark 1.2 has enough public results to be ranked (#48); Phi-3.5-mini does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Meta
MicrosoftSummary
- The widest gap is in coding, where Muse Spark 1.2 leads 49.2 to 34.6.
- Phi-3.5-mini has downloadable open weights; the other is API-only.
Side by side
| Muse Spark 1.2 | Phi-3.5-mini | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 50.3 | 36.9 |
| Released | 2026-08-05 | 2024-08-16 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 131K | — |
| Input $ / M tokens | $1.25 | — |
| Output $ / M tokens | $4.25 | — |
| Results tracked | 31 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.2 leads
Muse Spark 1.2: 49.2 (#51), Phi-3.5-mini: 34.6 (#232)
| Benchmark | Muse Spark 1.2 | Phi-3.5-mini |
|---|---|---|
| DeepSWE | 54.9% | — |
| LMArena WebDev | 1533 | — |
| FrontierSWE | 12% | — |
| SciCode | 56.4% | — |
| WeirdML | 60.3% | — |
| BigCodeBench Instruct | — | 32.8% |
| LMArena Coding | 1495 | — |
| BigCodeBench Complete | — | 38.5% |
Agentic & Tool Use Not comparable
Muse Spark 1.2: 29.4 (#87), Phi-3.5-mini: —
| Benchmark | Muse Spark 1.2 | Phi-3.5-mini |
|---|---|---|
| APEX-Agents | 36.4% | — |
| GDP.pdf | 16% | — |
Reasoning Not comparable
Muse Spark 1.2: 51.3 (#34), Phi-3.5-mini: —
| Benchmark | Muse Spark 1.2 | Phi-3.5-mini |
|---|---|---|
| SimpleBench | 74.5% | — |
| NYT Connections (extended) | 79.2% | — |
| CritPt | 17.7% | — |
| LMArena Hard Prompts | 1486 | — |
| DTBench | 94.7% | — |
| LMCA | 48.4% | — |
| Epoch Capabilities Index | 154.87 | — |
| PIQA | — | 81% |
Math Not comparable
Muse Spark 1.2: 46.4 (#70), Phi-3.5-mini: —
| Benchmark | Muse Spark 1.2 | Phi-3.5-mini |
|---|---|---|
| ProofBench | 43% | — |
| LMArena Math | 1471 | — |
| GSM8K | — | 86.2% |
Knowledge Not comparable
Muse Spark 1.2: 54.1 (#53), Phi-3.5-mini: —
| Benchmark | Muse Spark 1.2 | Phi-3.5-mini |
|---|---|---|
| SimpleQA Verified | 60.3% | — |
| LMArena Expert | 1480 | — |
| BoolQ | — | 78% |
Multimodal Not comparable
Muse Spark 1.2: 43.4 (#25), Phi-3.5-mini: —
| Benchmark | Muse Spark 1.2 | Phi-3.5-mini |
|---|---|---|
| LMArena Vision | 1305 | — |
Multilingual Not comparable
Muse Spark 1.2: 57.1 (#11), Phi-3.5-mini: —
| Benchmark | Muse Spark 1.2 | Phi-3.5-mini |
|---|---|---|
| LMArena Non-English | 1478 | — |
| LMArena Chinese | 1511 | — |
| LMArena French | 1513 | — |
| LMArena Russian | 1487 | — |
| LMArena Spanish | 1498 | — |
Instruction Following Not comparable
Muse Spark 1.2: 76.7 (#36), Phi-3.5-mini: —
| Benchmark | Muse Spark 1.2 | Phi-3.5-mini |
|---|---|---|
| LMArena Instruction Following | 1461 | — |
Long Context Not comparable
Muse Spark 1.2: 45.2 (#48), Phi-3.5-mini: —
| Benchmark | Muse Spark 1.2 | Phi-3.5-mini |
|---|---|---|
| LMArena Longer Query | 1475 | — |
Writing & Preference Not comparable
Muse Spark 1.2: 72.3 (#14), Phi-3.5-mini: —
| Benchmark | Muse Spark 1.2 | Phi-3.5-mini |
|---|---|---|
| LMArena Text | 1482 | — |
| LMArena Creative Writing | 1449 | — |
| EQ-Bench Creative Writing | 1840 | — |
| LMArena Multi-Turn | 1494 | — |
Frequently asked questions
Is Muse Spark 1.2 better than Phi-3.5-mini?
Muse Spark 1.2 has enough public results to be ranked (#48); Phi-3.5-mini does not yet, so treat this comparison as directional.
Is Muse Spark 1.2 or Phi-3.5-mini better for coding?
Muse Spark 1.2 scores higher on coding benchmarks: 49.2 versus 34.6 in the Noometry coding category.
How many benchmarks do Muse Spark 1.2 and Phi-3.5-mini share?
0 benchmarks have published results for both models. Muse Spark 1.2 has 31 scored results on Noometry and Phi-3.5-mini has 5.