Model comparison
GPT-5.2 vs Muse Spark 1.3
GPT-5.2 and Muse Spark 1.3 score almost the same on the Noometry Index (54.1 vs 54.8), so choose on price, context window or the category you care about most.
Last verified . 31 shared benchmarks.
MetaSummary
- They share 31 benchmarks with published results for both. GPT-5.2 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 knowledge, where GPT-5.2 leads 59.3 to 42.6.
- The biggest single-benchmark swing is ProofBench: 15% for GPT-5.2 and 58% for Muse Spark 1.3.
- Muse Spark 1.3 is cheaper at $1.25 / $4.25 per million input/output tokens, against $1.75 / $14 for GPT-5.2.
- Muse Spark 1.3 accepts more context: 1.05M tokens versus 400K.
Side by side
| GPT-5.2 | Muse Spark 1.3 | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 54.1 | 54.8 |
| Released | 2025-12-11 | 2026-09-02 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 1.05M |
| Max output | 128K | 131K |
| Input $ / M tokens | $1.75 | $1.25 |
| Output $ / M tokens | $14 | $4.25 |
| Results tracked | 67 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.3 leads
GPT-5.2: 51.6 (#37), Muse Spark 1.3: 56.6 (#21)
| Benchmark | GPT-5.2 | Muse Spark 1.3 |
|---|---|---|
| LMArena WebDev | 1416 | 1657 |
| LMArena Coding | 1447 | 1514 |
| SWE-bench Verified | 73.8% | — |
| SWE-bench Verified (bash only) | 72.8% | — |
| CursorBench | — | 41.6% |
| SWE-bench Multilingual | 66.7% | — |
| SciCode | — | 59.7% |
| GSO | 27.4% | — |
| WeirdML | 72.2% | — |
| ALE-Bench | 1,294 | — |
| AlgoTune | 2.05 | — |
Agentic & Tool Use GPT-5.2 leads
GPT-5.2: 40.2 (#24), Muse Spark 1.3: 38.6 (#30)
| Benchmark | GPT-5.2 | Muse Spark 1.3 |
|---|---|---|
| Terminal-Bench | 64.9% | — |
| APEX-Agents | — | 57.8% |
| Berkeley Function Calling Leaderboard | 55.9% | — |
| GDPval | 49.7% | — |
| Remote Labor Index | 2.5% | — |
| τ²-bench Airline | 83% | — |
| τ²-bench Banking | 32.2% | — |
| τ²-bench Retail | 81.6% | — |
| τ²-bench Telecom | 89.7% | — |
| DeepResearch Bench | 41.1% | — |
| GDP.pdf | — | 27.6% |
| LMArena Search | 1207 | — |
| METR Time Horizons | 75.3% | — |
| Vending-Bench 2 | 3,591 | — |
Reasoning Muse Spark 1.3 leads
GPT-5.2: 50.2 (#35), Muse Spark 1.3: 54.0 (#27)
| Benchmark | GPT-5.2 | Muse Spark 1.3 |
|---|---|---|
| NYT Connections (extended) | 83.6% | 85.1% |
| Chess Puzzles | 49% | 38% |
| LMArena Hard Prompts | 1445 | 1503 |
| Mystery Game Puzzles | 23% | 25% |
| DTBench | 90.9% | 96.5% |
| LMCA | 43.9% | 53.9% |
| Epoch Capabilities Index | 153.45 | 156.75 |
| ARC-AGI-2 | 52.9% | — |
| SimpleBench | 45.8% | — |
| Kagi LLM Benchmark | 73.3% | — |
| ARC-AGI-1 | 86.2% | — |
| CritPt | — | 26% |
| EnigmaEval | 10.4% | — |
| EBR-Bench | 23% | — |
| Bench to the Future 3 | — | 0.14 |
| ForecastBench | 60.1 | — |
Math Muse Spark 1.3 leads
GPT-5.2: 60.0 (#38), Muse Spark 1.3: 73.1 (#21)
| Benchmark | GPT-5.2 | Muse Spark 1.3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 67.4% | 74.4% |
| FrontierMath Tier 4 | 31.7% | 46.3% |
| OTIS Mock AIME 2024-2025 | 96.1% | 99.2% |
| ProofBench | 15% | 58% |
| LMArena Math | 1440 | 1494 |
| MathArena Final-Answer Competitions | 72% | — |
| FrontierMath (Feb 2025 set) | 40.7% | — |
| FrontierMath Tier 4 (v1) | 18.8% | — |
Knowledge GPT-5.2 leads
GPT-5.2: 59.3 (#32), Muse Spark 1.3: 42.6 (#95)
| Benchmark | GPT-5.2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Expert | 1445 | 1516 |
| GPQA Diamond | 91.4% | — |
| Humanity's Last Exam | 27.8% | — |
| SimpleQA Verified | 37.1% | — |
| Vectara Hallucination Rate | 8.4% | — |
Multimodal GPT-5.2 leads
GPT-5.2: 51.3 (#7), Muse Spark 1.3: 43.7 (#22)
| Benchmark | GPT-5.2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Vision | 1268 | 1309 |
| LMArena Document | 1405 | 1471 |
| VPCT | 84% | — |
| Furniture Assembly | 38.3% | — |
Multilingual Muse Spark 1.3 leads
GPT-5.2: 53.4 (#67), Muse Spark 1.3: 57.4 (#8)
| Benchmark | GPT-5.2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Non-English | 1425 | 1481 |
| LMArena Chinese | 1460 | 1529 |
| LMArena French | 1455 | 1524 |
| LMArena German | 1448 | 1515 |
| LMArena Japanese | 1420 | 1474 |
| LMArena Korean | 1392 | 1501 |
| LMArena Russian | 1440 | 1490 |
| LMArena Spanish | 1433 | 1490 |
Instruction Following Muse Spark 1.3 leads
GPT-5.2: 74.7 (#89), Muse Spark 1.3: 77.5 (#22)
| Benchmark | GPT-5.2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Instruction Following | 1417 | 1477 |
Long Context Muse Spark 1.3 leads
GPT-5.2: 44.0 (#78), Muse Spark 1.3: 45.6 (#32)
| Benchmark | GPT-5.2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Longer Query | 1428 | 1488 |
| CL-bench | 18.2% | — |
Writing & Preference Muse Spark 1.3 leads
GPT-5.2: 66.8 (#32), Muse Spark 1.3: 73.6 (#9)
| Benchmark | GPT-5.2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Text | 1439 | 1490 |
| LMArena Creative Writing | 1401 | 1455 |
| EQ-Bench Creative Writing | 1703 | 1906 |
| LMArena Multi-Turn | 1458 | 1482 |
Frequently asked questions
Is GPT-5.2 better than Muse Spark 1.3?
GPT-5.2 and Muse Spark 1.3 score almost the same on the Noometry Index (54.1 vs 54.8), so choose on price, context window or the category you care about most.
Which is cheaper, GPT-5.2 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-5.2 lists at $1.75 and $14.
Is GPT-5.2 or Muse Spark 1.3 better for coding?
Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 51.6 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-5.2 and Muse Spark 1.3 share?
31 benchmarks have published results for both models. GPT-5.2 has 67 scored results on Noometry and Muse Spark 1.3 has 37.