Model comparison
Muse Spark vs o3
Muse Spark is the stronger model overall, scoring 50.6 to 47.5 on the Noometry Index.
Last verified . 24 shared benchmarks.
MetaSummary
- They share 24 benchmarks with published results for both. Muse Spark scores higher in 6 categories and o3 in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 54.6.
- The biggest single-benchmark swing is Humanity's Last Exam: 40.6% for Muse Spark and 20.3% for o3.
Side by side
| Muse Spark | o3 | |
|---|---|---|
| Provider | Meta | OpenAI |
| Noometry Index | 50.6 | 47.5 |
| Released | 2026-04-08 | 2025-04-16 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $8 |
| Results tracked | 27 | 63 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Muse Spark: 46.2 (#69), o3: 46.8 (#64)
| Benchmark | Muse Spark | o3 |
|---|---|---|
| LMArena Coding | 1481 | 1408 |
| SWE-bench Verified | — | 62.3% |
| SWE-bench Verified (bash only) | — | 58.4% |
| Aider Polyglot | — | 81.3% |
| SciCode | 51.5% | — |
| GSO | — | 8.8% |
| WeirdML | — | 52.4% |
| CadEval | — | 74% |
| ALE-Bench | — | 933.55 |
Agentic & Tool Use Not comparable
Muse Spark: —, o3: 34.5 (#44)
| Benchmark | Muse Spark | o3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 30.8% |
| DeepResearch Bench | — | 45.2% |
| OSWorld | — | 23% |
| LMArena Search | — | 1144 |
| METR Time Horizons | — | 65.4% |
Reasoning Muse Spark leads
Muse Spark: 35.9 (#67), o3: 32.0 (#78)
| Benchmark | Muse Spark | o3 |
|---|---|---|
| CritPt | 11.3% | 1.4% |
| LMArena Hard Prompts | 1474 | 1402 |
| Epoch Capabilities Index | 152.04 | 146.86 |
| ARC-AGI-2 | — | 6.5% |
| SimpleBench | — | 53.1% |
| Kagi LLM Benchmark | — | 67.6% |
| ARC-AGI-1 | — | 60.8% |
| Chess Puzzles | — | 38% |
| EnigmaEval | — | 13.1% |
| Mystery Game Puzzles | — | 29% |
| DTBench | — | 84.8% |
| LMCA | — | 39.7% |
| ForecastBench | — | 62.5 |
Math o3 leads
Muse Spark: 47.8 (#66), o3: 50.2 (#58)
| Benchmark | Muse Spark | o3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 84.4% |
| LMArena Math | 1455 | 1426 |
| FrontierMath (Feb 2025 set) | 39% | 18.7% |
| FrontierMath Tier 4 (v1) | 14.6% | 2.1% |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| ProofBench | 17% | — |
| Omni-MATH | — | 71.4% |
| MATH Level 5 | — | 97.8% |
Knowledge Muse Spark leads
Muse Spark: 65.7 (#13), o3: 54.6 (#52)
| Benchmark | Muse Spark | o3 |
|---|---|---|
| GPQA Diamond | 89.8% | 81.8% |
| Humanity's Last Exam | 40.6% | 20.3% |
| LMArena Expert | 1457 | 1402 |
| SimpleQA Verified | — | 49.4% |
| MMLU-Pro | — | 85.9% |
| Confabulations | — | 14.4% |
| GPQA (HELM) | — | 75.3% |
Multimodal Muse Spark leads
Muse Spark: 43.4 (#24), o3: 41.4 (#36)
| Benchmark | Muse Spark | o3 |
|---|---|---|
| LMArena Vision | 1306 | 1214 |
| GeoBench | — | 74% |
| VPCT | — | 52% |
| LMArena Document | 1444 | — |
Multilingual Muse Spark leads
Muse Spark: 56.1 (#24), o3: 51.7 (#105)
| Benchmark | Muse Spark | o3 |
|---|---|---|
| LMArena Non-English | 1464 | 1401 |
| LMArena Chinese | 1509 | 1437 |
| LMArena French | 1497 | 1430 |
| LMArena German | 1497 | 1420 |
| LMArena Korean | 1459 | 1370 |
| LMArena Russian | 1466 | 1406 |
| LMArena Spanish | 1472 | 1395 |
| LMArena Japanese | — | 1403 |
Instruction Following Muse Spark leads
Muse Spark: 75.9 (#51), o3: 72.8 (#127)
| Benchmark | Muse Spark | o3 |
|---|---|---|
| LMArena Instruction Following | 1442 | 1368 |
| IFEval | — | 86.9% |
Long Context o3 leads
Muse Spark: 44.4 (#69), o3: 53.3 (#6)
| Benchmark | Muse Spark | o3 |
|---|---|---|
| LMArena Longer Query | 1451 | 1372 |
| Fiction.LiveBench | — | 88.9% |
| CL-bench | — | 17.8% |
Writing & Preference Muse Spark leads
Muse Spark: 66.0 (#39), o3: 63.5 (#64)
| Benchmark | Muse Spark | o3 |
|---|---|---|
| LMArena Text | 1474 | 1410 |
| LMArena Creative Writing | 1459 | 1359 |
| LMArena Multi-Turn | 1477 | 1405 |
| Short-Story Creative Writing | — | 83.9% |
| EQ-Bench Creative Writing | — | 1676 |
| WildBench | — | 86.1% |
Frequently asked questions
Is Muse Spark better than o3?
Muse Spark is the stronger model overall, scoring 50.6 to 47.5 on the Noometry Index.
Is Muse Spark or o3 better for coding?
They score almost the same on coding (46.2 vs 46.8); test both on your own repository before choosing.
How many benchmarks do Muse Spark and o3 share?
24 benchmarks have published results for both models. Muse Spark has 27 scored results on Noometry and o3 has 63.