Model comparison
Muse Glimmer vs Qwen2.5 72B Instruct
Muse Glimmer is the stronger model overall, scoring 41.7 to 31.9 on the Noometry Index.
Last verified . 12 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Muse Glimmer scores higher in 8 categories and Qwen2.5 72B Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Muse Glimmer leads 38.8 to 19.3.
Side by side
| Muse Glimmer | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 41.7 | 31.9 |
| Released | 2026-08-10 | 2024-09 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $1.40 |
| Output $ / M tokens | — | $5.60 |
| Results tracked | 15 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Glimmer leads
Muse Glimmer: 40.4 (#142), Qwen2.5 72B Instruct: 33.2 (#260)
| Benchmark | Muse Glimmer | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 1416 | 1292 |
| LMArena WebDev | 1355 | — |
| SciCode | 44.9% | — |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |
Agentic & Tool Use Not comparable
Muse Glimmer: —, Qwen2.5 72B Instruct: 22.1 (#133)
| Benchmark | Muse Glimmer | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning Muse Glimmer leads
Muse Glimmer: 25.7 (#144), Qwen2.5 72B Instruct: 22.3 (#199)
| Benchmark | Muse Glimmer | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1396 | 1271 |
| CritPt | 2.6% | — |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| Epoch Capabilities Index | — | 129 |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |
Math Muse Glimmer leads
Muse Glimmer: 38.8 (#125), Qwen2.5 72B Instruct: 19.3 (#287)
| Benchmark | Muse Glimmer | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Math | 1417 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |
Knowledge Muse Glimmer leads
Muse Glimmer: 38.5 (#143), Qwen2.5 72B Instruct: 27.0 (#253)
| Benchmark | Muse Glimmer | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Expert | 1386 | 1245 |
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |
Multilingual Muse Glimmer leads
Muse Glimmer: 50.5 (#122), Qwen2.5 72B Instruct: 41.0 (#213)
| Benchmark | Muse Glimmer | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1384 | 1252 |
| LMArena Chinese | 1412 | 1272 |
| LMArena Russian | 1390 | 1264 |
| LMArena French | — | 1280 |
| LMArena German | — | 1234 |
| LMArena Japanese | — | 1180 |
| LMArena Korean | — | 1188 |
| LMArena Spanish | — | 1256 |
Instruction Following Muse Glimmer leads
Muse Glimmer: 72.6 (#135), Qwen2.5 72B Instruct: 65.5 (#221)
| Benchmark | Muse Glimmer | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1375 | 1254 |
| IFEval | — | 80.6% |
Long Context Muse Glimmer leads
Muse Glimmer: 42.1 (#129), Qwen2.5 72B Instruct: 38.9 (#188)
| Benchmark | Muse Glimmer | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1382 | 1282 |
Writing & Preference Muse Glimmer leads
Muse Glimmer: 57.5 (#126), Qwen2.5 72B Instruct: 46.7 (#215)
| Benchmark | Muse Glimmer | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1389 | 1269 |
| LMArena Creative Writing | 1339 | 1221 |
| LMArena Multi-Turn | 1399 | 1272 |
| WildBench | — | 80.2% |
Frequently asked questions
Is Muse Glimmer better than Qwen2.5 72B Instruct?
Muse Glimmer is the stronger model overall, scoring 41.7 to 31.9 on the Noometry Index.
Is Muse Glimmer or Qwen2.5 72B Instruct better for coding?
Muse Glimmer scores higher on coding benchmarks: 40.4 versus 33.2 in the Noometry coding category.
How many benchmarks do Muse Glimmer and Qwen2.5 72B Instruct share?
12 benchmarks have published results for both models. Muse Glimmer has 15 scored results on Noometry and Qwen2.5 72B Instruct has 43.