Model comparison
GPT-5.4 Pro vs Muse Spark
GPT-5.4 Pro is the stronger model overall, scoring 58.8 to 50.3 on the Noometry Index.
Last verified . 6 shared benchmarks.
MetaSummary
- They share 6 benchmarks with published results for both. GPT-5.4 Pro scores higher in 3 categories and Muse Spark in 1 category; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.4 Pro leads 71.0 to 34.9.
- The biggest single-benchmark swing is CritPt: 30% for GPT-5.4 Pro and 11.3% for Muse Spark.
Side by side
| GPT-5.4 Pro | Muse Spark | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 58.8 | 50.3 |
| Released | 2026-03-05 | 2026-04-08 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | — |
| Max output | 128K | — |
| Input $ / M tokens | $30 | — |
| Output $ / M tokens | $180 | — |
| Results tracked | 16 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark leads
GPT-5.4 Pro: 42.6 (#89), Muse Spark: 45.6 (#65)
| Benchmark | GPT-5.4 Pro | Muse Spark |
|---|---|---|
| SciCode | — | 51.5% |
| WeirdML | 57.4% | — |
| LMArena Coding | — | 1482 |
Reasoning GPT-5.4 Pro leads
GPT-5.4 Pro: 71.0 (#10), Muse Spark: 34.9 (#61)
| Benchmark | GPT-5.4 Pro | Muse Spark |
|---|---|---|
| CritPt | 30% | 11.3% |
| Epoch Capabilities Index | 159.12 | 152.09 |
| ARC-AGI-2 | 83.3% | — |
| SimpleBench | 74.1% | — |
| ARC-AGI-1 | 94.5% | — |
| Chess Puzzles | 58.6% | — |
| EnigmaEval | 23.8% | — |
| LMArena Hard Prompts | — | 1475 |
Math GPT-5.4 Pro leads
GPT-5.4 Pro: 72.0 (#17), Muse Spark: 46.8 (#57)
| Benchmark | GPT-5.4 Pro | Muse Spark |
|---|---|---|
| FrontierMath (Feb 2025 set) | 50% | 39% |
| FrontierMath Tier 4 (v1) | 37.5% | 14.6% |
| FrontierMath (Tiers 1-3) | 82.5% | — |
| FrontierMath Tier 4 | 58.5% | — |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 17% |
| LMArena Math | — | 1455 |
Knowledge GPT-5.4 Pro leads
GPT-5.4 Pro: 68.3 (#6), Muse Spark: 65.7 (#12)
| Benchmark | GPT-5.4 Pro | Muse Spark |
|---|---|---|
| GPQA Diamond | 94.6% | 89.8% |
| Humanity's Last Exam | 44.3% | 40.6% |
| SimpleQA Verified | 46.3% | — |
| Vectara Hallucination Rate | 8.3% | — |
| LMArena Expert | — | 1458 |
Multimodal Not comparable
GPT-5.4 Pro: —, Muse Spark: 42.7 (#23)
| Benchmark | GPT-5.4 Pro | Muse Spark |
|---|---|---|
| LMArena Vision | — | 1306 |
| LMArena Document | — | 1444 |
Multilingual Not comparable
GPT-5.4 Pro: —, Muse Spark: 56.3 (#23)
| Benchmark | GPT-5.4 Pro | Muse Spark |
|---|---|---|
| LMArena Non-English | — | 1464 |
| LMArena Chinese | — | 1507 |
| LMArena French | — | 1497 |
| LMArena German | — | 1497 |
| LMArena Korean | — | 1457 |
| LMArena Russian | — | 1467 |
| LMArena Spanish | — | 1471 |
Instruction Following Not comparable
GPT-5.4 Pro: —, Muse Spark: 76.1 (#47)
| Benchmark | GPT-5.4 Pro | Muse Spark |
|---|---|---|
| LMArena Instruction Following | — | 1443 |
Long Context Not comparable
GPT-5.4 Pro: —, Muse Spark: 44.4 (#65)
| Benchmark | GPT-5.4 Pro | Muse Spark |
|---|---|---|
| LMArena Longer Query | — | 1451 |
Writing & Preference Not comparable
GPT-5.4 Pro: —, Muse Spark: 66.2 (#37)
| Benchmark | GPT-5.4 Pro | Muse Spark |
|---|---|---|
| LMArena Text | — | 1474 |
| LMArena Creative Writing | — | 1460 |
| LMArena Multi-Turn | — | 1477 |
Frequently asked questions
Is GPT-5.4 Pro better than Muse Spark?
GPT-5.4 Pro is the stronger model overall, scoring 58.8 to 50.3 on the Noometry Index.
Is GPT-5.4 Pro or Muse Spark better for coding?
Muse Spark scores higher on coding benchmarks: 45.6 versus 42.6 in the Noometry coding category.
How many benchmarks do GPT-5.4 Pro and Muse Spark share?
6 benchmarks have published results for both models. GPT-5.4 Pro has 16 scored results on Noometry and Muse Spark has 27.