Model comparison
GPT-5.4 mini vs Muse Spark 1.3
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 45.0 on the Noometry Index.
Last verified . 32 shared benchmarks.
MetaSummary
- They share 32 benchmarks with published results for both. GPT-5.4 mini scores higher in 1 category and Muse Spark 1.3 in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Muse Spark 1.3 leads 73.1 to 45.5.
- The biggest single-benchmark swing is ProofBench: 21% for GPT-5.4 mini and 58% for Muse Spark 1.3.
- GPT-5.4 mini is cheaper at $0.75 / $4.50 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.3.
- Muse Spark 1.3 accepts more context: 1.05M tokens versus 400K.
Side by side
| GPT-5.4 mini | Muse Spark 1.3 | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 45.0 | 54.8 |
| Released | 2026-03-17 | 2026-09-02 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 1.05M |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.75 | $1.25 |
| Output $ / M tokens | $4.50 | $4.25 |
| Results tracked | 46 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.3 leads
GPT-5.4 mini: 45.2 (#72), Muse Spark 1.3: 56.6 (#21)
| Benchmark | GPT-5.4 mini | Muse Spark 1.3 |
|---|---|---|
| LMArena WebDev | 1397 | 1657 |
| SciCode | 49.9% | 59.7% |
| LMArena Coding | 1438 | 1514 |
| FrontierCode | 27% | — |
| CursorBench | — | 41.6% |
| WeirdML | 60.3% | — |
| ALE-Bench | 1,189 | — |
Agentic & Tool Use Muse Spark 1.3 leads
GPT-5.4 mini: 29.9 (#81), Muse Spark 1.3: 38.6 (#30)
| Benchmark | GPT-5.4 mini | Muse Spark 1.3 |
|---|---|---|
| APEX-Agents | — | 57.8% |
| DeepResearch Bench | 36.3% | — |
| GDP.pdf | — | 27.6% |
Reasoning Muse Spark 1.3 leads
GPT-5.4 mini: 30.4 (#85), Muse Spark 1.3: 54.0 (#27)
| Benchmark | GPT-5.4 mini | Muse Spark 1.3 |
|---|---|---|
| NYT Connections (extended) | 61.8% | 85.1% |
| CritPt | 10% | 26% |
| Chess Puzzles | 24% | 38% |
| LMArena Hard Prompts | 1424 | 1503 |
| Mystery Game Puzzles | 11% | 25% |
| DTBench | 80% | 96.5% |
| LMCA | 40.8% | 53.9% |
| Epoch Capabilities Index | 148.84 | 156.75 |
| ARC-AGI-2 | 18.9% | — |
| Kagi LLM Benchmark | 37.9% | — |
| ARC-AGI-1 | 63.7% | — |
| Thematic Generalization | 61.7% | — |
| Bench to the Future 3 | — | 0.14 |
| ForecastBench | 57 | — |
Math Muse Spark 1.3 leads
GPT-5.4 mini: 45.5 (#75), Muse Spark 1.3: 73.1 (#21)
| Benchmark | GPT-5.4 mini | Muse Spark 1.3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 51.2% | 74.4% |
| FrontierMath Tier 4 | 9.8% | 46.3% |
| OTIS Mock AIME 2024-2025 | 88.9% | 99.2% |
| ProofBench | 21% | 58% |
| LMArena Math | 1419 | 1494 |
| FrontierMath (Feb 2025 set) | 28.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GPT-5.4 mini leads
GPT-5.4 mini: 51.5 (#67), Muse Spark 1.3: 42.6 (#95)
| Benchmark | GPT-5.4 mini | Muse Spark 1.3 |
|---|---|---|
| LMArena Expert | 1435 | 1516 |
| GPQA Diamond | 86.9% | — |
| SimpleQA Verified | 29.4% | — |
| Vectara Hallucination Rate | 5.5% | — |
Multimodal Muse Spark 1.3 leads
GPT-5.4 mini: 39.7 (#56), Muse Spark 1.3: 43.7 (#22)
| Benchmark | GPT-5.4 mini | Muse Spark 1.3 |
|---|---|---|
| LMArena Vision | 1245 | 1309 |
| LMArena Document | — | 1471 |
Multilingual Muse Spark 1.3 leads
GPT-5.4 mini: 51.9 (#96), Muse Spark 1.3: 57.4 (#8)
| Benchmark | GPT-5.4 mini | Muse Spark 1.3 |
|---|---|---|
| LMArena Non-English | 1405 | 1481 |
| LMArena Chinese | 1446 | 1529 |
| LMArena French | 1440 | 1524 |
| LMArena German | 1409 | 1515 |
| LMArena Japanese | 1374 | 1474 |
| LMArena Korean | 1368 | 1501 |
| LMArena Russian | 1417 | 1490 |
| LMArena Spanish | 1405 | 1490 |
Instruction Following Muse Spark 1.3 leads
GPT-5.4 mini: 74.1 (#102), Muse Spark 1.3: 77.5 (#22)
| Benchmark | GPT-5.4 mini | Muse Spark 1.3 |
|---|---|---|
| LMArena Instruction Following | 1405 | 1477 |
Long Context Muse Spark 1.3 leads
GPT-5.4 mini: 43.0 (#112), Muse Spark 1.3: 45.6 (#32)
| Benchmark | GPT-5.4 mini | Muse Spark 1.3 |
|---|---|---|
| LMArena Longer Query | 1407 | 1488 |
Writing & Preference Muse Spark 1.3 leads
GPT-5.4 mini: 64.0 (#58), Muse Spark 1.3: 73.6 (#9)
| Benchmark | GPT-5.4 mini | Muse Spark 1.3 |
|---|---|---|
| LMArena Text | 1412 | 1490 |
| LMArena Creative Writing | 1370 | 1455 |
| EQ-Bench Creative Writing | 1665 | 1906 |
| LMArena Multi-Turn | 1429 | 1482 |
Frequently asked questions
Is GPT-5.4 mini better than Muse Spark 1.3?
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 45.0 on the Noometry Index.
Which is cheaper, GPT-5.4 mini or Muse Spark 1.3?
GPT-5.4 mini is cheaper. It lists at $0.75 per million input tokens and $4.50 per million output tokens; Muse Spark 1.3 lists at $1.25 and $4.25.
Is GPT-5.4 mini or Muse Spark 1.3 better for coding?
Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 45.2 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.3 does, with 1.05M tokens against 400K.
How many benchmarks do GPT-5.4 mini and Muse Spark 1.3 share?
32 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Muse Spark 1.3 has 37.