Model comparison
GPT-5 vs Muse Spark 1.3
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 50.9 on the Noometry Index.
Last verified . 31 shared benchmarks.
MetaSummary
- They share 31 benchmarks with published results for both. GPT-5 scores higher in 3 categories and Muse Spark 1.3 in 7 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in long context, where GPT-5 leads 69.5 to 45.6.
- The biggest single-benchmark swing is ProofBench: 18% for GPT-5 and 58% for Muse Spark 1.3.
- Muse Spark 1.3 is cheaper at $1.25 / $4.25 per million input/output tokens, against $1.25 / $10 for GPT-5.
- Muse Spark 1.3 accepts more context: 1.05M tokens versus 400K.
Side by side
| GPT-5 | Muse Spark 1.3 | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 50.9 | 54.8 |
| Released | 2025-08-07 | 2026-09-02 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 1.05M |
| Max output | 128K | 131K |
| Input $ / M tokens | $1.25 | $1.25 |
| Output $ / M tokens | $10 | $4.25 |
| Results tracked | 69 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.3 leads
GPT-5: 50.3 (#47), Muse Spark 1.3: 56.6 (#21)
| Benchmark | GPT-5 | Muse Spark 1.3 |
|---|---|---|
| LMArena WebDev | 1418 | 1657 |
| SciCode | 42.9% | 59.7% |
| LMArena Coding | 1436 | 1514 |
| SWE-bench Verified | 73.6% | — |
| SWE-bench Verified (bash only) | 65% | — |
| Aider Polyglot | 88% | — |
| CursorBench | — | 41.6% |
| GSO | 6.9% | — |
| WeirdML | 60.7% | — |
| ALE-Bench | 1,162 | — |
| AlgoTune | 1.67 | — |
Agentic & Tool Use Muse Spark 1.3 leads
GPT-5: 33.1 (#56), Muse Spark 1.3: 38.6 (#30)
| Benchmark | GPT-5 | Muse Spark 1.3 |
|---|---|---|
| Terminal-Bench | 49.6% | — |
| APEX-Agents | — | 57.8% |
| GDPval | 34.8% | — |
| Remote Labor Index | 1.7% | — |
| DeepResearch Bench | 49.6% | — |
| BALROG | 32.8% | — |
| GDP.pdf | — | 27.6% |
| LMArena Search | 1133 | — |
| METR Time Horizons | 69.6% | — |
Reasoning Muse Spark 1.3 leads
GPT-5: 38.3 (#64), Muse Spark 1.3: 54.0 (#27)
| Benchmark | GPT-5 | Muse Spark 1.3 |
|---|---|---|
| CritPt | 12.6% | 26% |
| Chess Puzzles | 37% | 38% |
| LMArena Hard Prompts | 1416 | 1503 |
| Mystery Game Puzzles | 23% | 25% |
| DTBench | 90.7% | 96.5% |
| LMCA | 40% | 53.9% |
| Epoch Capabilities Index | 150 | 156.75 |
| ARC-AGI-2 | 9.9% | — |
| SimpleBench | 56.7% | — |
| Kagi LLM Benchmark | 72.7% | — |
| NYT Connections (extended) | — | 85.1% |
| ARC-AGI-1 | 65.7% | — |
| EnigmaEval | 10.5% | — |
| EBR-Bench | 12.7% | — |
| Bench to the Future 3 | — | 0.14 |
| ForecastBench | 61.4 | — |
Math Muse Spark 1.3 leads
GPT-5: 55.0 (#44), Muse Spark 1.3: 73.1 (#21)
| Benchmark | GPT-5 | Muse Spark 1.3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 55.4% | 74.4% |
| FrontierMath Tier 4 | 22% | 46.3% |
| OTIS Mock AIME 2024-2025 | 91.4% | 99.2% |
| ProofBench | 18% | 58% |
| LMArena Math | 1407 | 1494 |
| Omni-MATH | 64.7% | — |
| MATH Level 5 | 98.1% | — |
| FrontierMath (Feb 2025 set) | 32.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge GPT-5 leads
GPT-5: 56.6 (#43), Muse Spark 1.3: 42.6 (#95)
| Benchmark | GPT-5 | Muse Spark 1.3 |
|---|---|---|
| LMArena Expert | 1419 | 1516 |
| GPQA Diamond | 86.2% | — |
| Humanity's Last Exam | 25.3% | — |
| SimpleQA Verified | 50.1% | — |
| MMLU-Pro | 86.3% | — |
| Confabulations | 10.3% | — |
| Vectara Hallucination Rate | 14.7% | — |
| GPQA (HELM) | 79.2% | — |
Multimodal GPT-5 leads
GPT-5: 46.8 (#13), Muse Spark 1.3: 43.7 (#22)
| Benchmark | GPT-5 | Muse Spark 1.3 |
|---|---|---|
| LMArena Vision | 1232 | 1309 |
| GeoBench | 81% | — |
| VPCT | 66% | — |
| LMArena Document | — | 1471 |
Multilingual Muse Spark 1.3 leads
GPT-5: 51.4 (#110), Muse Spark 1.3: 57.4 (#8)
| Benchmark | GPT-5 | Muse Spark 1.3 |
|---|---|---|
| LMArena Non-English | 1397 | 1481 |
| LMArena Chinese | 1422 | 1529 |
| LMArena French | 1410 | 1524 |
| LMArena German | 1416 | 1515 |
| LMArena Japanese | 1409 | 1474 |
| LMArena Korean | 1360 | 1501 |
| LMArena Russian | 1406 | 1490 |
| LMArena Spanish | 1399 | 1490 |
Instruction Following Muse Spark 1.3 leads
GPT-5: 73.8 (#113), Muse Spark 1.3: 77.5 (#22)
| Benchmark | GPT-5 | Muse Spark 1.3 |
|---|---|---|
| LMArena Instruction Following | 1388 | 1477 |
| IFEval | 87.5% | — |
Long Context GPT-5 leads
GPT-5: 69.5 (#2), Muse Spark 1.3: 45.6 (#32)
| Benchmark | GPT-5 | Muse Spark 1.3 |
|---|---|---|
| LMArena Longer Query | 1399 | 1488 |
| Fiction.LiveBench | 97.2% | — |
Writing & Preference Muse Spark 1.3 leads
GPT-5: 63.4 (#65), Muse Spark 1.3: 73.6 (#9)
| Benchmark | GPT-5 | Muse Spark 1.3 |
|---|---|---|
| LMArena Text | 1406 | 1490 |
| LMArena Creative Writing | 1365 | 1455 |
| EQ-Bench Creative Writing | 1627 | 1906 |
| LMArena Multi-Turn | 1426 | 1482 |
| Short-Story Creative Writing | 86% | — |
| WildBench | 85.7% | — |
Frequently asked questions
Is GPT-5 better than Muse Spark 1.3?
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 50.9 on the Noometry Index.
Which is cheaper, GPT-5 or Muse Spark 1.3?
Muse Spark 1.3 is cheaper. It lists at $1.25 per million input tokens and $4.25 per million output tokens; GPT-5 lists at $1.25 and $10.
Is GPT-5 or Muse Spark 1.3 better for coding?
Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 50.3 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 and Muse Spark 1.3 share?
31 benchmarks have published results for both models. GPT-5 has 69 scored results on Noometry and Muse Spark 1.3 has 37.