Model comparison
Muse Spark 1.2 vs o3
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 47.5 on the Noometry Index.
Last verified . 23 shared benchmarks.
MetaSummary
- They share 23 benchmarks with published results for both. Muse Spark 1.2 scores higher in 6 categories and o3 in 4 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.2 leads 51.3 to 32.0.
- The biggest single-benchmark swing is SimpleBench: 74.5% for Muse Spark 1.2 and 53.1% for o3.
- Muse Spark 1.2 is cheaper at $1.25 / $4.25 per million input/output tokens, against $2 / $8 for o3.
- Muse Spark 1.2 accepts more context: 1.05M tokens versus 200K.
Side by side
| Muse Spark 1.2 | o3 | |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 50.3 | 47.5 |
| Released | 2026-08-05 | 2025-04-16 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 200K |
| Max output | 131K | 100K |
| Input $ / M tokens | $1.25 | $2 |
| Output $ / M tokens | $4.25 | $8 |
| Results tracked | 31 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.2 leads
Muse Spark 1.2: 49.2 (#51), o3: 46.8 (#64)
| Benchmark | Muse Spark 1.2 | o3 |
|---|---|---|
| WeirdML | 60.3% | 52.4% |
| LMArena Coding | 1495 | 1408 |
| SWE-bench Verified | — | 62.3% |
| DeepSWE | 54.9% | — |
| SWE-bench Verified (bash only) | — | 58.4% |
| Aider Polyglot | — | 81.3% |
| LMArena WebDev | 1533 | — |
| FrontierSWE | 12% | — |
| SciCode | 56.4% | — |
| GSO | — | 8.8% |
| CadEval | — | 74% |
| ALE-Bench | — | 933.55 |
Agentic & Tool Use o3 leads
Muse Spark 1.2: 29.4 (#87), o3: 34.5 (#44)
| Benchmark | Muse Spark 1.2 | o3 |
|---|---|---|
| APEX-Agents | 36.4% | — |
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 30.8% |
| DeepResearch Bench | — | 45.2% |
| OSWorld | — | 23% |
| GDP.pdf | 16% | — |
| LMArena Search | — | 1144 |
| METR Time Horizons | — | 65.4% |
Reasoning Muse Spark 1.2 leads
Muse Spark 1.2: 51.3 (#34), o3: 32.0 (#78)
| Benchmark | Muse Spark 1.2 | o3 |
|---|---|---|
| SimpleBench | 74.5% | 53.1% |
| CritPt | 17.7% | 1.4% |
| LMArena Hard Prompts | 1486 | 1402 |
| DTBench | 94.7% | 84.8% |
| LMCA | 48.4% | 39.7% |
| Epoch Capabilities Index | 154.87 | 146.86 |
| ARC-AGI-2 | — | 6.5% |
| Kagi LLM Benchmark | — | 67.6% |
| NYT Connections (extended) | 79.2% | — |
| ARC-AGI-1 | — | 60.8% |
| Chess Puzzles | — | 38% |
| EnigmaEval | — | 13.1% |
| Mystery Game Puzzles | — | 29% |
| ForecastBench | — | 62.5 |
Math o3 leads
Muse Spark 1.2: 46.4 (#70), o3: 50.2 (#58)
| Benchmark | Muse Spark 1.2 | o3 |
|---|---|---|
| LMArena Math | 1471 | 1426 |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| OTIS Mock AIME 2024-2025 | — | 84.4% |
| ProofBench | 43% | — |
| Omni-MATH | — | 71.4% |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 18.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge Too close to call
Muse Spark 1.2: 54.1 (#53), o3: 54.6 (#52)
| Benchmark | Muse Spark 1.2 | o3 |
|---|---|---|
| SimpleQA Verified | 60.3% | 49.4% |
| LMArena Expert | 1480 | 1402 |
| GPQA Diamond | — | 81.8% |
| Humanity's Last Exam | — | 20.3% |
| MMLU-Pro | — | 85.9% |
| Confabulations | — | 14.4% |
| GPQA (HELM) | — | 75.3% |
Multimodal Muse Spark 1.2 leads
Muse Spark 1.2: 43.4 (#25), o3: 41.4 (#36)
| Benchmark | Muse Spark 1.2 | o3 |
|---|---|---|
| LMArena Vision | 1305 | 1214 |
| GeoBench | — | 74% |
| VPCT | — | 52% |
Multilingual Muse Spark 1.2 leads
Muse Spark 1.2: 57.1 (#11), o3: 51.7 (#105)
| Benchmark | Muse Spark 1.2 | o3 |
|---|---|---|
| LMArena Non-English | 1478 | 1401 |
| LMArena Chinese | 1511 | 1437 |
| LMArena French | 1513 | 1430 |
| LMArena Russian | 1487 | 1406 |
| LMArena Spanish | 1498 | 1395 |
| LMArena German | — | 1420 |
| LMArena Japanese | — | 1403 |
| LMArena Korean | — | 1370 |
Instruction Following Muse Spark 1.2 leads
Muse Spark 1.2: 76.7 (#36), o3: 72.8 (#127)
| Benchmark | Muse Spark 1.2 | o3 |
|---|---|---|
| LMArena Instruction Following | 1461 | 1368 |
| IFEval | — | 86.9% |
Long Context o3 leads
Muse Spark 1.2: 45.2 (#48), o3: 53.3 (#6)
| Benchmark | Muse Spark 1.2 | o3 |
|---|---|---|
| LMArena Longer Query | 1475 | 1372 |
| Fiction.LiveBench | — | 88.9% |
| CL-bench | — | 17.8% |
Writing & Preference Muse Spark 1.2 leads
Muse Spark 1.2: 72.3 (#14), o3: 63.5 (#64)
| Benchmark | Muse Spark 1.2 | o3 |
|---|---|---|
| LMArena Text | 1482 | 1410 |
| LMArena Creative Writing | 1449 | 1359 |
| EQ-Bench Creative Writing | 1840 | 1676 |
| LMArena Multi-Turn | 1494 | 1405 |
| Short-Story Creative Writing | — | 83.9% |
| WildBench | — | 86.1% |
Frequently asked questions
Is Muse Spark 1.2 better than o3?
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 47.5 on the Noometry Index.
Which is cheaper, Muse Spark 1.2 or o3?
Muse Spark 1.2 is cheaper. It lists at $1.25 per million input tokens and $4.25 per million output tokens; o3 lists at $2 and $8.
Is Muse Spark 1.2 or o3 better for coding?
Muse Spark 1.2 scores higher on coding benchmarks: 49.2 versus 46.8 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.2 does, with 1.05M tokens against 200K.
How many benchmarks do Muse Spark 1.2 and o3 share?
23 benchmarks have published results for both models. Muse Spark 1.2 has 31 scored results on Noometry and o3 has 63.