Model comparison
GPT-4 vs Muse Spark
Muse Spark is the stronger model overall, scoring 50.6 to 29.1 on the Noometry Index.
Last verified . 19 shared benchmarks.
MetaSummary
- They share 19 benchmarks with published results for both. GPT-4 scores higher in 0 categories and Muse Spark in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 18.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.1% for GPT-4 and 88.9% for Muse Spark.
Side by side
| GPT-4 | Muse Spark | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 29.1 | 50.6 |
| Released | 2023-03-14 | 2026-04-08 |
| Weights | Proprietary | Proprietary |
| Context window | 8K | — |
| Max output | 8K | — |
| Input $ / M tokens | $30 | — |
| Output $ / M tokens | $60 | — |
| Results tracked | 38 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark leads
GPT-4: 31.6 (#283), Muse Spark: 46.2 (#69)
| Benchmark | GPT-4 | Muse Spark |
|---|---|---|
| LMArena Coding | 1254 | 1481 |
| SciCode | — | 51.5% |
| WeirdML | 12.4% | — |
| BigCodeBench Instruct | 46% | — |
| BigCodeBench Complete | 57.2% | — |
| HumanEval+ | 79.3% | — |
Agentic & Tool Use Not comparable
GPT-4: —, Muse Spark: —
| Benchmark | GPT-4 | Muse Spark |
|---|---|---|
| METR Time Horizons | 36.1% | — |
Reasoning Muse Spark leads
GPT-4: 17.8 (#289), Muse Spark: 35.9 (#67)
| Benchmark | GPT-4 | Muse Spark |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1474 |
| Epoch Capabilities Index | 125.89 | 152.04 |
| CritPt | — | 11.3% |
| Chess Puzzles | 4% | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 62.7% | — |
| LMCA | 17.1% | — |
| BIG-Bench Hard | 75.1% | — |
| ForecastBench | 57.8 | — |
| HellaSwag | 95.3% | — |
| WinoGrande | 87.5% | — |
Math Muse Spark leads
GPT-4: 10.8 (#309), Muse Spark: 47.8 (#66)
| Benchmark | GPT-4 | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | 88.9% |
| LMArena Math | 1269 | 1455 |
| ProofBench | — | 17% |
| MATH Level 5 | 23% | — |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
| GSM8K | 92% | — |
Knowledge Muse Spark leads
GPT-4: 18.4 (#282), Muse Spark: 65.7 (#13)
| Benchmark | GPT-4 | Muse Spark |
|---|---|---|
| GPQA Diamond | 35.7% | 89.8% |
| LMArena Expert | 1211 | 1457 |
| Humanity's Last Exam | — | 40.6% |
| MMLU | 86.4% | — |
| TriviaQA | 84.8% | — |
Multimodal Not comparable
GPT-4: —, Muse Spark: 43.4 (#24)
| Benchmark | GPT-4 | Muse Spark |
|---|---|---|
| LMArena Vision | — | 1306 |
| LMArena Document | — | 1444 |
Multilingual Muse Spark leads
GPT-4: 40.6 (#215), Muse Spark: 56.1 (#24)
| Benchmark | GPT-4 | Muse Spark |
|---|---|---|
| LMArena Non-English | 1246 | 1464 |
| LMArena Chinese | 1242 | 1509 |
| LMArena French | 1283 | 1497 |
| LMArena German | 1251 | 1497 |
| LMArena Korean | 1184 | 1459 |
| LMArena Russian | 1251 | 1466 |
| LMArena Spanish | 1261 | 1472 |
| LMArena Japanese | 1209 | — |
Instruction Following Muse Spark leads
GPT-4: 65.3 (#222), Muse Spark: 75.9 (#51)
| Benchmark | GPT-4 | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1241 | 1442 |
Long Context Muse Spark leads
GPT-4: 37.7 (#212), Muse Spark: 44.4 (#69)
| Benchmark | GPT-4 | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1244 | 1451 |
Writing & Preference Muse Spark leads
GPT-4: 34.9 (#268), Muse Spark: 66.0 (#39)
| Benchmark | GPT-4 | Muse Spark |
|---|---|---|
| LMArena Text | 1263 | 1474 |
| LMArena Creative Writing | 1244 | 1459 |
| LMArena Multi-Turn | 1257 | 1477 |
| EQ-Bench Creative Writing | 752 | — |
Frequently asked questions
Is GPT-4 better than Muse Spark?
Muse Spark is the stronger model overall, scoring 50.6 to 29.1 on the Noometry Index.
Is GPT-4 or Muse Spark better for coding?
Muse Spark scores higher on coding benchmarks: 46.2 versus 31.6 in the Noometry coding category.
How many benchmarks do GPT-4 and Muse Spark share?
19 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Muse Spark has 27.