Model comparison
Muse Spark 1.1 vs Phi-4 Mini
Muse Spark 1.1 is the stronger model overall, scoring 49.9 to 30.9 on the Noometry Index. Phi-4 Mini costs 15× less per token, which makes it the better buy when Muse Spark 1.1's lead doesn't matter for your workload.
Last verified . 2 shared benchmarks.
Meta
MicrosoftSummary
- They share 2 benchmarks with published results for both. Muse Spark 1.1 scores higher in 3 categories and Phi-4 Mini in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark 1.1 leads 53.1 to 25.3.
- The biggest single-benchmark swing is SciCode: 58.8% for Muse Spark 1.1 and 10.8% for Phi-4 Mini.
- Phi-4 Mini is cheaper at $0.075 / $0.30 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.1.
- Muse Spark 1.1 accepts more context: 1.05M tokens versus 128K.
- Phi-4 Mini has downloadable open weights; the other is API-only.
Side by side
| Muse Spark 1.1 | Phi-4 Mini | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 49.9 | 30.9 |
| Released | 2026-04-08 | 2024-12-11 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 128K |
| Max output | 131K | 4K |
| Input $ / M tokens | $1.25 | $0.075 |
| Output $ / M tokens | $4.25 | $0.30 |
| Results tracked | 37 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.1 leads
Muse Spark 1.1: 51.3 (#40), Phi-4 Mini: 28.1 (#317)
| Benchmark | Muse Spark 1.1 | Phi-4 Mini |
|---|---|---|
| SciCode | 58.8% | 10.8% |
| DeepSWE | 53.3% | — |
| LMArena WebDev | 1542 | — |
| LMArena Coding | 1498 | — |
Agentic & Tool Use Not comparable
Muse Spark 1.1: 30.8 (#73), Phi-4 Mini: —
| Benchmark | Muse Spark 1.1 | Phi-4 Mini |
|---|---|---|
| APEX-Agents | 31.8% | — |
| τ²-bench Banking | 40.5% | — |
| GBAEval | 7.9% | — |
| GDP.pdf | 15% | — |
| Vending-Bench 2 | 6,520 | — |
Reasoning Muse Spark 1.1 leads
Muse Spark 1.1: 47.1 (#44), Phi-4 Mini: 22.4 (#195)
| Benchmark | Muse Spark 1.1 | Phi-4 Mini |
|---|---|---|
| CritPt | 15.1% | 0% |
| NYT Connections (extended) | 84.9% | — |
| LMArena Hard Prompts | 1486 | — |
| DTBench | 94.4% | — |
| LMCA | 49.9% | — |
| Surface Evolver Bench | 52.5% | — |
| Epoch Capabilities Index | 154.21 | — |
Math Not comparable
Muse Spark 1.1: 45.5 (#76), Phi-4 Mini: —
| Benchmark | Muse Spark 1.1 | Phi-4 Mini |
|---|---|---|
| ProofBench | 39% | — |
| LMArena Math | 1483 | — |
Knowledge Muse Spark 1.1 leads
Muse Spark 1.1: 53.1 (#59), Phi-4 Mini: 25.3 (#262)
| Benchmark | Muse Spark 1.1 | Phi-4 Mini |
|---|---|---|
| SimpleQA Verified | 57.8% | — |
| Vectara Hallucination Rate | — | 23.5% |
| LMArena Expert | 1478 | — |
Multimodal Not comparable
Muse Spark 1.1: 42.6 (#29), Phi-4 Mini: —
| Benchmark | Muse Spark 1.1 | Phi-4 Mini |
|---|---|---|
| LMArena Vision | 1293 | — |
| LMArena Document | 1465 | — |
Multilingual Not comparable
Muse Spark 1.1: 56.7 (#17), Phi-4 Mini: —
| Benchmark | Muse Spark 1.1 | Phi-4 Mini |
|---|---|---|
| LMArena Non-English | 1472 | — |
| LMArena Chinese | 1518 | — |
| LMArena French | 1494 | — |
| LMArena German | 1466 | — |
| LMArena Japanese | 1451 | — |
| LMArena Korean | 1458 | — |
| LMArena Russian | 1483 | — |
| LMArena Spanish | 1464 | — |
Instruction Following Not comparable
Muse Spark 1.1: 76.5 (#39), Phi-4 Mini: —
| Benchmark | Muse Spark 1.1 | Phi-4 Mini |
|---|---|---|
| LMArena Instruction Following | 1457 | — |
Long Context Not comparable
Muse Spark 1.1: 44.8 (#58), Phi-4 Mini: —
| Benchmark | Muse Spark 1.1 | Phi-4 Mini |
|---|---|---|
| LMArena Longer Query | 1462 | — |
Writing & Preference Not comparable
Muse Spark 1.1: 73.4 (#11), Phi-4 Mini: —
| Benchmark | Muse Spark 1.1 | Phi-4 Mini |
|---|---|---|
| LMArena Text | 1479 | — |
| LMArena Creative Writing | 1437 | — |
| EQ-Bench Creative Writing | 1927 | — |
| EQ-Bench 4 | 1260 | — |
| LMArena Multi-Turn | 1485 | — |
Frequently asked questions
Is Muse Spark 1.1 better than Phi-4 Mini?
Muse Spark 1.1 is the stronger model overall, scoring 49.9 to 30.9 on the Noometry Index. Phi-4 Mini costs 15× less per token, which makes it the better buy when Muse Spark 1.1's lead doesn't matter for your workload.
Which is cheaper, Muse Spark 1.1 or Phi-4 Mini?
Phi-4 Mini is cheaper. It lists at $0.075 per million input tokens and $0.30 per million output tokens; Muse Spark 1.1 lists at $1.25 and $4.25.
Is Muse Spark 1.1 or Phi-4 Mini better for coding?
Muse Spark 1.1 scores higher on coding benchmarks: 51.3 versus 28.1 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.1 does, with 1.05M tokens against 128K.
How many benchmarks do Muse Spark 1.1 and Phi-4 Mini share?
2 benchmarks have published results for both models. Muse Spark 1.1 has 37 scored results on Noometry and Phi-4 Mini has 3.