Model comparison
Llama 2-7B vs Muse Glimmer
Muse Glimmer is the stronger model overall, scoring 41.3 to 28.6 on the Noometry Index.
Last verified . 12 shared benchmarks.
MetaSummary
- They share 12 benchmarks with published results for both. Llama 2-7B scores higher in 0 categories and Muse Glimmer in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Muse Glimmer leads 57.7 to 28.1.
Side by side
| Llama 2-7B | Muse Glimmer | |
|---|---|---|
| Provider | Meta | Meta |
| Noometry Index | 28.6 | 41.3 |
| Released | 2023-07-18 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 29 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Glimmer leads
Llama 2-7B: 28.7 (#302), Muse Glimmer: 38.7 (#157)
| Benchmark | Llama 2-7B | Muse Glimmer |
|---|---|---|
| LMArena Coding | 1002 | 1417 |
| LMArena WebDev | — | 1355 |
Reasoning Muse Glimmer leads
Llama 2-7B: 15.1 (#309), Muse Glimmer: 27.2 (#111)
| Benchmark | Llama 2-7B | Muse Glimmer |
|---|---|---|
| LMArena Hard Prompts | 1009 | 1395 |
| Chess Puzzles | 0% | — |
| BIG-Bench Hard | 39.2% | — |
| Epoch Capabilities Index | 98.54 | — |
| HellaSwag | 77.2% | — |
| LAMBADA | 73.3% | — |
| PIQA | 78.8% | — |
| WinoGrande | 69.2% | — |
Math Muse Glimmer leads
Llama 2-7B: 28.2 (#231), Muse Glimmer: 36.1 (#128)
| Benchmark | Llama 2-7B | Muse Glimmer |
|---|---|---|
| LMArena Math | 1042 | 1419 |
| GSM8K | 16.7% | — |
Knowledge Muse Glimmer leads
Llama 2-7B: 27.7 (#243), Muse Glimmer: 37.9 (#140)
| Benchmark | Llama 2-7B | Muse Glimmer |
|---|---|---|
| LMArena Expert | 1036 | 1388 |
| ARC (AI2) Challenge | 45.9% | — |
| BoolQ | 77.9% | — |
| MMLU | 45.8% | — |
| OpenBookQA | 58.6% | — |
| TriviaQA | 73.7% | — |
Multimodal Not comparable
Llama 2-7B: —, Muse Glimmer: —
| Benchmark | Llama 2-7B | Muse Glimmer |
|---|---|---|
| ScienceQA | 43.1% | — |
Multilingual Muse Glimmer leads
Llama 2-7B: 23.9 (#288), Muse Glimmer: 50.6 (#117)
| Benchmark | Llama 2-7B | Muse Glimmer |
|---|---|---|
| LMArena Non-English | 973 | 1384 |
| LMArena Chinese | 973 | 1412 |
| LMArena Russian | 995 | 1393 |
| LMArena French | 969 | — |
| LMArena German | 978 | — |
| LMArena Spanish | 1007 | — |
Instruction Following Muse Glimmer leads
Llama 2-7B: 51.0 (#293), Muse Glimmer: 72.7 (#134)
| Benchmark | Llama 2-7B | Muse Glimmer |
|---|---|---|
| LMArena Instruction Following | 1006 | 1374 |
Long Context Muse Glimmer leads
Llama 2-7B: 30.4 (#282), Muse Glimmer: 42.1 (#124)
| Benchmark | Llama 2-7B | Muse Glimmer |
|---|---|---|
| LMArena Longer Query | 999 | 1381 |
Writing & Preference Muse Glimmer leads
Llama 2-7B: 28.1 (#293), Muse Glimmer: 57.7 (#122)
| Benchmark | Llama 2-7B | Muse Glimmer |
|---|---|---|
| LMArena Text | 1053 | 1389 |
| LMArena Creative Writing | 1033 | 1338 |
| LMArena Multi-Turn | 1029 | 1398 |
Frequently asked questions
Is Llama 2-7B better than Muse Glimmer?
Muse Glimmer is the stronger model overall, scoring 41.3 to 28.6 on the Noometry Index.
Is Llama 2-7B or Muse Glimmer better for coding?
Muse Glimmer scores higher on coding benchmarks: 38.7 versus 28.7 in the Noometry coding category.
How many benchmarks do Llama 2-7B and Muse Glimmer share?
12 benchmarks have published results for both models. Llama 2-7B has 29 scored results on Noometry and Muse Glimmer has 13.