Model comparison
GPT-4.1 vs Muse Spark 1.2
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 35.9 on the Noometry Index.
Last verified . 22 shared benchmarks.
MetaSummary
- They share 22 benchmarks with published results for both. GPT-4.1 scores higher in 1 category and Muse Spark 1.2 in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.2 leads 51.3 to 11.7.
- The biggest single-benchmark swing is SimpleBench: 27% for GPT-4.1 and 74.5% for Muse Spark 1.2.
- Muse Spark 1.2 is cheaper at $1.25 / $4.25 per million input/output tokens, against $2 / $8 for GPT-4.1.
- Muse Spark 1.2 accepts more context: 1.05M tokens versus 1.05M.
Side by side
| GPT-4.1 | Muse Spark 1.2 | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 35.9 | 50.3 |
| Released | 2025-04-14 | 2026-08-05 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 33K | 131K |
| Input $ / M tokens | $2 | $1.25 |
| Output $ / M tokens | $8 | $4.25 |
| Results tracked | 52 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.2 leads
GPT-4.1: 34.4 (#238), Muse Spark 1.2: 49.2 (#51)
| Benchmark | GPT-4.1 | Muse Spark 1.2 |
|---|---|---|
| WeirdML | 39% | 60.3% |
| LMArena Coding | 1391 | 1495 |
| SWE-bench Verified | 48.5% | — |
| DeepSWE | — | 54.9% |
| SWE-bench Verified (bash only) | 39.6% | — |
| Aider Polyglot | 52.4% | — |
| LMArena WebDev | — | 1533 |
| FrontierSWE | — | 12% |
| SciCode | — | 56.4% |
| CadEval | 42% | — |
| ALE-Bench | 558.1 | — |
Agentic & Tool Use GPT-4.1 leads
GPT-4.1: 34.7 (#43), Muse Spark 1.2: 29.4 (#87)
| Benchmark | GPT-4.1 | Muse Spark 1.2 |
|---|---|---|
| APEX-Agents | — | 36.4% |
| Berkeley Function Calling Leaderboard | 54% | — |
| GDP.pdf | — | 16% |
Reasoning Muse Spark 1.2 leads
GPT-4.1: 11.7 (#339), Muse Spark 1.2: 51.3 (#34)
| Benchmark | GPT-4.1 | Muse Spark 1.2 |
|---|---|---|
| SimpleBench | 27% | 74.5% |
| LMArena Hard Prompts | 1384 | 1486 |
| DTBench | 68.3% | 94.7% |
| LMCA | 25.6% | 48.4% |
| Epoch Capabilities Index | 136.78 | 154.87 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 52.3% | — |
| NYT Connections (extended) | — | 79.2% |
| ARC-AGI-1 | 5.5% | — |
| CritPt | — | 17.7% |
| Chess Puzzles | 6% | — |
| EnigmaEval | 2.2% | — |
| ForecastBench | 61.5 | — |
Math Muse Spark 1.2 leads
GPT-4.1: 22.3 (#280), Muse Spark 1.2: 46.4 (#70)
| Benchmark | GPT-4.1 | Muse Spark 1.2 |
|---|---|---|
| LMArena Math | 1370 | 1471 |
| FrontierMath (Tiers 1-3) | 6% | — |
| OTIS Mock AIME 2024-2025 | 38.3% | — |
| ProofBench | — | 43% |
| Omni-MATH | 47.1% | — |
| MATH Level 5 | 83% | — |
| FrontierMath (Feb 2025 set) | 5.5% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Muse Spark 1.2 leads
GPT-4.1: 37.1 (#160), Muse Spark 1.2: 54.1 (#53)
| Benchmark | GPT-4.1 | Muse Spark 1.2 |
|---|---|---|
| SimpleQA Verified | 31.1% | 60.3% |
| LMArena Expert | 1364 | 1480 |
| GPQA Diamond | 66.9% | — |
| Humanity's Last Exam | 5.4% | — |
| MMLU-Pro | 81.1% | — |
| Vectara Hallucination Rate | 5.6% | — |
| GPQA (HELM) | 65.9% | — |
Multimodal Muse Spark 1.2 leads
GPT-4.1: 38.2 (#67), Muse Spark 1.2: 43.4 (#25)
| Benchmark | GPT-4.1 | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | 1211 | 1305 |
| GeoBench | 72% | — |
Multilingual Muse Spark 1.2 leads
GPT-4.1: 49.4 (#133), Muse Spark 1.2: 57.1 (#11)
| Benchmark | GPT-4.1 | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | 1370 | 1478 |
| LMArena Chinese | 1382 | 1511 |
| LMArena French | 1382 | 1513 |
| LMArena Russian | 1377 | 1487 |
| LMArena Spanish | 1376 | 1498 |
| LMArena German | 1381 | — |
| LMArena Japanese | 1319 | — |
| LMArena Korean | 1339 | — |
Instruction Following Muse Spark 1.2 leads
GPT-4.1: 71.3 (#153), Muse Spark 1.2: 76.7 (#36)
| Benchmark | GPT-4.1 | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | 1367 | 1461 |
| IFEval | 83.8% | — |
Long Context Muse Spark 1.2 leads
GPT-4.1: 40.0 (#163), Muse Spark 1.2: 45.2 (#48)
| Benchmark | GPT-4.1 | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | 1385 | 1475 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference Muse Spark 1.2 leads
GPT-4.1: 57.6 (#125), Muse Spark 1.2: 72.3 (#14)
| Benchmark | GPT-4.1 | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | 1383 | 1482 |
| LMArena Creative Writing | 1363 | 1449 |
| EQ-Bench Creative Writing | 1420 | 1840 |
| LMArena Multi-Turn | 1398 | 1494 |
| WildBench | 85.4% | — |
Frequently asked questions
Is GPT-4.1 better than Muse Spark 1.2?
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 35.9 on the Noometry Index.
Which is cheaper, GPT-4.1 or Muse Spark 1.2?
Muse Spark 1.2 is cheaper. It lists at $1.25 per million input tokens and $4.25 per million output tokens; GPT-4.1 lists at $2 and $8.
Is GPT-4.1 or Muse Spark 1.2 better for coding?
Muse Spark 1.2 scores higher on coding benchmarks: 49.2 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.2 does, with 1.05M tokens against 1.05M.
How many benchmarks do GPT-4.1 and Muse Spark 1.2 share?
22 benchmarks have published results for both models. GPT-4.1 has 52 scored results on Noometry and Muse Spark 1.2 has 31.