Model comparison
GPT-4 Turbo vs Muse Glimmer
Muse Glimmer is the stronger model overall, scoring 41.3 to 30.3 on the Noometry Index.
Last verified . 12 shared benchmarks.
MetaSummary
- They share 12 benchmarks with published results for both. GPT-4 Turbo scores higher in 0 categories and Muse Glimmer in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Muse Glimmer leads 36.1 to 8.6.
- Muse Glimmer has downloadable open weights; the other is API-only.
Side by side
| GPT-4 Turbo | Muse Glimmer | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 30.3 | 41.3 |
| Released | 2023-11-06 | — |
| Weights | Proprietary | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $10 | — |
| Output $ / M tokens | $30 | — |
| Results tracked | 36 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Glimmer leads
GPT-4 Turbo: 33.4 (#247), Muse Glimmer: 38.7 (#157)
| Benchmark | GPT-4 Turbo | Muse Glimmer |
|---|---|---|
| LMArena Coding | 1268 | 1417 |
| LMArena WebDev | — | 1355 |
| WeirdML | 18% | — |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 58.2% | — |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Not comparable
GPT-4 Turbo: —, Muse Glimmer: —
| Benchmark | GPT-4 Turbo | Muse Glimmer |
|---|---|---|
| METR Time Horizons | 36.7% | — |
Reasoning Muse Glimmer leads
GPT-4 Turbo: 14.9 (#311), Muse Glimmer: 27.2 (#111)
| Benchmark | GPT-4 Turbo | Muse Glimmer |
|---|---|---|
| LMArena Hard Prompts | 1251 | 1395 |
| SimpleBench | 25.1% | — |
| Chess Puzzles | 6% | — |
| DTBench | 61.6% | — |
| LMCA | 9.8% | — |
| Epoch Capabilities Index | 127.25 | — |
| ForecastBench | 59.4 | — |
Math Muse Glimmer leads
GPT-4 Turbo: 8.6 (#316), Muse Glimmer: 36.1 (#128)
| Benchmark | GPT-4 Turbo | Muse Glimmer |
|---|---|---|
| LMArena Math | 1272 | 1419 |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| OTIS Mock AIME 2024-2025 | 6.7% | — |
| MATH Level 5 | 46.7% | — |
Knowledge Muse Glimmer leads
GPT-4 Turbo: 24.3 (#263), Muse Glimmer: 37.9 (#140)
| Benchmark | GPT-4 Turbo | Muse Glimmer |
|---|---|---|
| LMArena Expert | 1223 | 1388 |
| GPQA Diamond | 46.6% | — |
| Confabulations | 28.4% | — |
| MMLU | 81.3% | — |
Multimodal Not comparable
GPT-4 Turbo: 30.0 (#104), Muse Glimmer: —
| Benchmark | GPT-4 Turbo | Muse Glimmer |
|---|---|---|
| LMArena Vision | 1090 | — |
Multilingual Muse Glimmer leads
GPT-4 Turbo: 40.7 (#211), Muse Glimmer: 50.6 (#117)
| Benchmark | GPT-4 Turbo | Muse Glimmer |
|---|---|---|
| LMArena Non-English | 1245 | 1384 |
| LMArena Chinese | 1242 | 1412 |
| LMArena Russian | 1259 | 1393 |
| LMArena French | 1275 | — |
| LMArena German | 1259 | — |
| LMArena Japanese | 1194 | — |
| LMArena Korean | 1187 | — |
| LMArena Spanish | 1260 | — |
Instruction Following Muse Glimmer leads
GPT-4 Turbo: 66.0 (#211), Muse Glimmer: 72.7 (#134)
| Benchmark | GPT-4 Turbo | Muse Glimmer |
|---|---|---|
| LMArena Instruction Following | 1250 | 1374 |
Long Context Muse Glimmer leads
GPT-4 Turbo: 38.0 (#200), Muse Glimmer: 42.1 (#124)
| Benchmark | GPT-4 Turbo | Muse Glimmer |
|---|---|---|
| LMArena Longer Query | 1254 | 1381 |
Writing & Preference Muse Glimmer leads
GPT-4 Turbo: 47.9 (#201), Muse Glimmer: 57.7 (#122)
| Benchmark | GPT-4 Turbo | Muse Glimmer |
|---|---|---|
| LMArena Text | 1272 | 1389 |
| LMArena Creative Writing | 1269 | 1338 |
| LMArena Multi-Turn | 1267 | 1398 |
Frequently asked questions
Is GPT-4 Turbo better than Muse Glimmer?
Muse Glimmer is the stronger model overall, scoring 41.3 to 30.3 on the Noometry Index.
Is GPT-4 Turbo or Muse Glimmer better for coding?
Muse Glimmer scores higher on coding benchmarks: 38.7 versus 33.4 in the Noometry coding category.
How many benchmarks do GPT-4 Turbo and Muse Glimmer share?
12 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Muse Glimmer has 13.