Model comparison
Muse Glimmer vs phi-3-medium 14B
Muse Glimmer is the stronger model overall, scoring 41.3 to 29.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
Meta
MicrosoftSummary
- The widest gap is in knowledge, where Muse Glimmer leads 37.9 to 9.1.
Side by side
| Muse Glimmer | phi-3-medium 14B | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 41.3 | 29.1 |
| Released | — | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 13 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Glimmer leads
Muse Glimmer: 38.7 (#157), phi-3-medium 14B: 36.3 (#198)
| Benchmark | Muse Glimmer | phi-3-medium 14B |
|---|---|---|
| LMArena WebDev | 1355 | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1417 | — |
| BigCodeBench Complete | — | 48.7% |
Reasoning Not comparable
Muse Glimmer: 27.2 (#111), phi-3-medium 14B: —
| Benchmark | Muse Glimmer | phi-3-medium 14B |
|---|---|---|
| LMArena Hard Prompts | 1395 | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| Epoch Capabilities Index | — | 121.18 |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math Muse Glimmer leads
Muse Glimmer: 36.1 (#128), phi-3-medium 14B: 25.2 (#249)
| Benchmark | Muse Glimmer | phi-3-medium 14B |
|---|---|---|
| LMArena Math | 1419 | — |
| MATH Level 5 | — | 17.6% |
Knowledge Muse Glimmer leads
Muse Glimmer: 37.9 (#140), phi-3-medium 14B: 9.1 (#301)
| Benchmark | Muse Glimmer | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | — | 27.6% |
| LMArena Expert | 1388 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multilingual Not comparable
Muse Glimmer: 50.6 (#117), phi-3-medium 14B: —
| Benchmark | Muse Glimmer | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1384 | — |
| LMArena Chinese | 1412 | — |
| LMArena Russian | 1393 | — |
Instruction Following Not comparable
Muse Glimmer: 72.7 (#134), phi-3-medium 14B: —
| Benchmark | Muse Glimmer | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1374 | — |
Long Context Not comparable
Muse Glimmer: 42.1 (#124), phi-3-medium 14B: —
| Benchmark | Muse Glimmer | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1381 | — |
Writing & Preference Not comparable
Muse Glimmer: 57.7 (#122), phi-3-medium 14B: —
| Benchmark | Muse Glimmer | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1389 | — |
| LMArena Creative Writing | 1338 | — |
| LMArena Multi-Turn | 1398 | — |
Frequently asked questions
Is Muse Glimmer better than phi-3-medium 14B?
Muse Glimmer is the stronger model overall, scoring 41.3 to 29.1 on the Noometry Index.
Is Muse Glimmer or phi-3-medium 14B better for coding?
Muse Glimmer scores higher on coding benchmarks: 38.7 versus 36.3 in the Noometry coding category.
How many benchmarks do Muse Glimmer and phi-3-medium 14B share?
0 benchmarks have published results for both models. Muse Glimmer has 13 scored results on Noometry and phi-3-medium 14B has 13.