Model comparison
MiniMax-M3 vs Muse Spark
Muse Spark is the stronger model overall, scoring 50.6 to 43.8 on the Noometry Index.
Last verified . 24 shared benchmarks.
Summary
- They share 24 benchmarks with published results for both. MiniMax-M3 scores higher in 0 categories and Muse Spark in 9 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Muse Spark leads 47.8 to 40.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 71.1% for MiniMax-M3 and 88.9% for Muse Spark.
- MiniMax-M3 has downloadable open weights; the other is API-only.
Side by side
| MiniMax-M3 | Muse Spark | |
|---|---|---|
| Provider | MiniMax | Meta |
| Noometry Index | 43.8 | 50.6 |
| Released | 2026-06-01 | 2026-04-08 |
| Weights | Open | Proprietary |
| Context window | 1M | — |
| Max output | 512K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 41 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark leads
MiniMax-M3: 41.8 (#118), Muse Spark: 46.2 (#69)
| Benchmark | MiniMax-M3 | Muse Spark |
|---|---|---|
| SciCode | 47.1% | 51.5% |
| LMArena Coding | 1469 | 1481 |
| FrontierCode | 14.7% | — |
| LMArena WebDev | 1482 | — |
| ALE-Bench | 640.02 | — |
Agentic & Tool Use Not comparable
MiniMax-M3: 22.6 (#130), Muse Spark: —
| Benchmark | MiniMax-M3 | Muse Spark |
|---|---|---|
| APEX-Agents | 37.7% | — |
| OSWorld 2.0 | 4.6% | — |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 2,158 | — |
Reasoning Muse Spark leads
MiniMax-M3: 30.1 (#87), Muse Spark: 35.9 (#67)
| Benchmark | MiniMax-M3 | Muse Spark |
|---|---|---|
| CritPt | 3.7% | 11.3% |
| LMArena Hard Prompts | 1447 | 1474 |
| Epoch Capabilities Index | 146.95 | 152.04 |
| SimpleBench | 45.8% | — |
| NYT Connections (extended) | 65.1% | — |
| Chess Puzzles | 14% | — |
| Mystery Game Puzzles | 8% | — |
| DTBench | 78.9% | — |
| LMCA | 33.7% | — |
| Surface Evolver Bench | 55% | — |
| ForecastBench | 61.4 | — |
Math Muse Spark leads
MiniMax-M3: 40.0 (#95), Muse Spark: 47.8 (#66)
| Benchmark | MiniMax-M3 | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 88.9% |
| ProofBench | 18% | 17% |
| LMArena Math | 1429 | 1455 |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Muse Spark leads
MiniMax-M3: 58.4 (#35), Muse Spark: 65.7 (#13)
| Benchmark | MiniMax-M3 | Muse Spark |
|---|---|---|
| GPQA Diamond | 90.9% | 89.8% |
| LMArena Expert | 1461 | 1457 |
| Humanity's Last Exam | — | 40.6% |
Multimodal Muse Spark leads
MiniMax-M3: 40.2 (#51), Muse Spark: 43.4 (#24)
| Benchmark | MiniMax-M3 | Muse Spark |
|---|---|---|
| LMArena Vision | 1253 | 1306 |
| LMArena Document | 1435 | 1444 |
Multilingual Muse Spark leads
MiniMax-M3: 53.0 (#75), Muse Spark: 56.1 (#24)
| Benchmark | MiniMax-M3 | Muse Spark |
|---|---|---|
| LMArena Non-English | 1420 | 1464 |
| LMArena Chinese | 1463 | 1509 |
| LMArena French | 1447 | 1497 |
| LMArena German | 1426 | 1497 |
| LMArena Korean | 1372 | 1459 |
| LMArena Russian | 1428 | 1466 |
| LMArena Spanish | 1432 | 1472 |
| LMArena Japanese | 1381 | — |
Instruction Following Too close to call
MiniMax-M3: 75.5 (#62), Muse Spark: 75.9 (#51)
| Benchmark | MiniMax-M3 | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1433 | 1442 |
Long Context Too close to call
MiniMax-M3: 44.2 (#72), Muse Spark: 44.4 (#69)
| Benchmark | MiniMax-M3 | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1445 | 1451 |
Writing & Preference Muse Spark leads
MiniMax-M3: 62.1 (#83), Muse Spark: 66.0 (#39)
| Benchmark | MiniMax-M3 | Muse Spark |
|---|---|---|
| LMArena Text | 1433 | 1474 |
| LMArena Creative Writing | 1404 | 1459 |
| LMArena Multi-Turn | 1442 | 1477 |
| EQ-Bench 4 | 1150 | — |
Frequently asked questions
Is MiniMax-M3 better than Muse Spark?
Muse Spark is the stronger model overall, scoring 50.6 to 43.8 on the Noometry Index.
Is MiniMax-M3 or Muse Spark better for coding?
Muse Spark scores higher on coding benchmarks: 46.2 versus 41.8 in the Noometry coding category.
How many benchmarks do MiniMax-M3 and Muse Spark share?
24 benchmarks have published results for both models. MiniMax-M3 has 41 scored results on Noometry and Muse Spark has 27.